Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to individuals involved in legal contexts, particularly focusing on patients, defendants, and inmates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to the central participant or subject (person, animal, or designated entity) being discussed or instructed in the passage.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab

    people and animals

    np_max-act-logits · gpt-5Triggered by @arielgoldsteinlab

    specific entity

    np_max-act-logits · gemini-2.5-flashTriggered by @arielgoldsteinlab

    words and pronouns referring to people, such as "child," "inmate," "she," and "they."

    oai_token-act-pair · gemini-2.5-flashTriggered by @arielgoldsteinlab

    Explanation could not be parsed.

    eleuther_acts_top20 · gpt-5Triggered by @arielgoldsteinlab

    These are all tokens referring to a person or animal that is the subject of an action.

    eleuther_acts_top20 · gemini-2.5-flashTriggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    verläs
    -0.61
    shadowRadius
    -0.60
    ignty
    -0.58
    URLException
    -0.57
    CppCodeGen
    -0.56
    PickerController
    -0.55
     Crimes
    -0.53
    landse
    -0.52
    sern
    -0.51
    positories
    -0.50
    POSITIVE LOGITS
    évaluateur
    0.63
     ujednoznacz
    0.59
    TestBed
    0.55
     who
    0.53
     يتيمه
    0.53
    self
    0.52
    oids
    0.50
    олові
    0.50
    ’
    0.49
    '
    0.49
    Act Density 0.739%

    No Known Activations