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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "self" and related phrases indicating self-reference or self-organization concepts

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

    occurrences of the word "self" and its variations, particularly in programming or technical contexts

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

    self-attributed terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yarnpkg
    -0.57
    :+:
    -0.56
     跳转至
    -0.54
    verwijspagina
    -0.54
    ędzynarod
    -0.50
    existent
    -0.50
     Horacio
    -0.49
    antMatchers
    -0.49
    ipedi
    -0.49
    )}</
    -0.48
    POSITIVE LOGITS
    WebControls
    0.60
    MessageState
    0.56
    tonsoft
    0.55
     tull
    0.53
     iyo
    0.51
    ntax
    0.48
    setDo
    0.48
    ToLeft
    0.48
    uction
    0.48
    hogy
    0.47
    Act Density 0.015%

    No Known Activations