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

    Neuronpedia

    INDEX
    Explanations

    mentions of historical events or actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Footnote
    -0.60
    Nation
    -0.59
    âĨĴ
    -0.58
    izable
    -0.57
    stood
    -0.57
    arta
    -0.57
     marker
    -0.56
     Millions
    -0.56
     spheres
    -0.54
     buckets
    -0.54
    POSITIVE LOGITS
    hes
    1.05
    wolves
    1.02
     born
    0.96
    wolf
    0.96
    abi
    0.88
     founded
    0.86
     originally
    0.85
     released
    0.84
     spotted
    0.82
     sentenced
    0.81
    Act Density 0.115%

    No Known Activations