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

    Neuronpedia

    INDEX
    Explanations

    mentions of significant events or achievements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.79
    lang
    -0.70
    gery
    -0.69
    peed
    -0.67
    politics
    -0.66
    ractions
    -0.66
    lag
    -0.66
    til
    -0.64
    olia
    -0.63
    iety
    -0.62
    POSITIVE LOGITS
     ever
    1.01
     responders
    0.92
     batch
    0.91
     baseman
    0.91
     glimpse
    0.90
     EVER
    0.89
     installment
    0.88
    ever
    0.87
     foray
    0.87
     anniversary
    0.84
    Act Density 0.143%

    No Known Activations