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

    Neuronpedia

    INDEX
    Explanations

    historical and contextual age references in sentences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     captcha
    -0.72
    abilia
    -0.68
     Horizon
    -0.63
     Collider
    -0.63
     DRAG
    -0.58
     organizers
    -0.55
     balance
    -0.54
     Marketplace
    -0.54
    balance
    -0.53
     contingency
    -0.53
    POSITIVE LOGITS
    ties
    1.09
    s
    1.08
     twenties
    0.99
    ixties
    0.98
    th
    0.97
    ies
    0.87
    years
    0.86
     years
    0.81
    ieth
    0.80
    something
    0.78
    Act Density 0.063%

    No Known Activations