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

    Neuronpedia

    INDEX
    Explanations

    conjunctions used to provide contrast or introduce a different perspective

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocument
    -0.68
     identified
    -0.66
    reported
    -0.65
    ewitness
    -0.65
     extensively
    -0.64
    eteen
    -0.64
    tained
    -0.64
    irteen
    -0.63
    ONSORED
    -0.63
    endar
    -0.62
    POSITIVE LOGITS
     yeah
    0.92
     thats
    0.85
     maybe
    0.84
    maybe
    0.82
     devs
    0.81
     beware
    0.79
     hopefully
    0.79
     hey
    0.77
     Goku
    0.77
     dont
    0.76
    Act Density 0.618%

    No Known Activations