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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the implementation or commencement of rules, regulations, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITS
    -0.17
     slim
    -0.16
    کت
    -0.15
    iers
    -0.15
     sno
    -0.15
    quest
    -0.15
    SETTING
    -0.15
     bare
    -0.15
     event
    -0.14
     siblings
    -0.14
    POSITIVE LOGITS
    bomb
    0.15
     Prairie
    0.15
     Deferred
    0.14
    ynes
    0.14
     normalization
    0.14
    ibold
    0.13
    letic
    0.13
    normalized
    0.13
    far
    0.13
    ited
    0.13
    Act Density 0.018%

    No Known Activations