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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns, conjunctions, and verbs.

    oai_token-act-pair · gemini-2.0-flash

    presence of the word "I"

    np_token-act-pair-logits · gpt-4o-mini

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NewUrlParser
    -0.66
     FetchType
    -0.58
     createState
    -0.55
     thon
    -0.55
    पया
    -0.54
     springfox
    -0.53
    ksesta
    -0.52
     (++
    -0.50
    ónimos
    -0.50
     _('
    -0.50
    POSITIVE LOGITS
     just
    0.84
    just
    0.71
    Just
    0.68
     Just
    0.68
     JUST
    0.59
     its
    0.55
     Its
    0.52
    Its
    0.52
    enumi
    0.52
     ddelweddau
    0.50
    Act Density 0.595%

    No Known Activations