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

    Neuronpedia

    INDEX
    Explanations

    statements made within a political context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    uum
    -0.70
    iliated
    -0.70
    ccording
    -0.64
    arin
    -0.64
    keley
    -0.64
    uilt
    -0.63
    orks
    -0.63
    ecause
    -0.63
    Åį
    -0.62
    amily
    -0.61
    POSITIVE LOGITS
     spree
    0.91
    fulness
    0.79
    steps
    0.74
    iques
    0.71
    ings
    0.67
     regarding
    0.67
     exploits
    0.67
     rampage
    0.67
     selections
    0.64
     foray
    0.63
    Act Density 11.439%

    No Known Activations