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

    Neuronpedia

    INDEX
    Explanations

    phrases describing the condition and quality of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     voks
    -0.16
     trá»ĭ
    -0.14
    atti
    -0.14
     Talent
    -0.14
     Rica
    -0.14
     ê³µìĭĿ
    -0.13
    áÅĻ
    -0.13
    rog
    -0.13
     aggress
    -0.13
    umph
    -0.13
    POSITIVE LOGITS
     condition
    0.78
     Condition
    0.66
    condition
    0.60
    Condition
    0.56
     CONDITION
    0.55
    -condition
    0.45
    _condition
    0.44
    .condition
    0.42
    (condition
    0.41
    CONDITION
    0.41
    Act Density 0.102%

    No Known Activations