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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and political entities

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

    references to countries or nationalities.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
    ⓘ
    -0.52
    类型的
    -0.49
     type
    -0.48
    atimes
    -0.47
    î
    -0.44
    types
    -0.44
    type
    -0.42
    usters
    -0.42
     Answer
    -0.41
    €.
    -0.41
    POSITIVE LOGITS
     Efq
    0.85
    featureID
    0.84
     myſelf
    0.83
    makeConstraints
    0.77
     itſelf
    0.76
     protoimpl
    0.75
    IntoConstraints
    0.74
     كومونز
    0.73
    uxxxx
    0.71
    ########.
    0.71
    Act Density 0.453%

    No Known Activations