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

    Neuronpedia

    INDEX
    Explanations

    occurrences of variable declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    incinn
    -0.15
    nid
    -0.15
    ارک
    -0.14
    ÙĨÚ¯
    -0.14
     Weiner
    -0.14
    amarin
    -0.14
    vla
    -0.13
    chts
    -0.13
    inary
    -0.13
     IReadOnly
    -0.13
    POSITIVE LOGITS
    264
    0.16
    -collapse
    0.15
    abol
    0.15
     Clintons
    0.14
     reform
    0.14
     given
    0.14
    yan
    0.13
    ynn
    0.13
    getter
    0.13
    abile
    0.13
    Act Density 0.052%

    No Known Activations