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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or "if" clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dep
    -0.15
     ton
    -0.15
    al
    -0.14
    .pt
    -0.14
    ego
    -0.14
    401
    -0.14
    oss
    -0.14
     належ
    -0.14
    877
    -0.14
    fil
    -0.14
    POSITIVE LOGITS
    ogle
    0.16
    thalm
    0.15
    ź
    0.14
     Skipping
    0.14
    аниÑĨ
    0.14
    teki
    0.14
    rame
    0.14
    夫
    0.14
    ublik
    0.14
     Marketable
    0.13
    Act Density 0.148%

    No Known Activations