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

    Neuronpedia

    INDEX
    Explanations

    requests or appeals for action or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve requests or inquiries for assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥ¬
    -0.76
    âĶĢâĶĢ
    -0.70
     Nanto
    -0.70
    ccording
    -0.69
    marine
    -0.67
    cutting
    -0.66
     Cock
    -0.64
    smoking
    -0.63
     Surv
    -0.63
     Broadcasting
    -0.61
    POSITIVE LOGITS
     rhet
    1.07
     questions
    1.00
     probing
    0.97
    naires
    0.97
    ioned
    0.94
    erville
    0.91
    govtrack
    0.86
    ingly
    0.84
    wered
    0.82
    FontSize
    0.80
    Act Density 0.042%

    No Known Activations