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

    Neuronpedia

    INDEX
    Explanations

    historical events or biographical information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    :/
    -0.69
    abe
    -0.65
    ounty
    -0.61
     unemploy
    -0.60
    $$
    -0.60
     constitu
    -0.58
     selves
    -0.57
     unequivocally
    -0.56
    weights
    -0.56
    reon
    -0.56
    POSITIVE LOGITS
     addition
    1.34
     spite
    1.23
    juries
    1.18
     hindsight
    1.16
    coming
    1.12
    flation
    1.11
    jured
    1.10
     contrast
    1.10
     retrospect
    1.08
     accordance
    1.08
    Act Density 0.132%

    No Known Activations