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

    Neuronpedia

    INDEX
    Explanations

    mentions of uncertainties or speculative events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     embra
    -1.26
     emphat
    -1.16
     accla
    -1.08
     Simult
    -1.04
     sputnik
    -1.04
     compen
    -1.04
     maneu
    -1.04
     immen
    -1.04
     applau
    -1.02
     pessi
    -1.02
    POSITIVE LOGITS
     might
    1.05
     may
    1.03
     maybe
    0.98
     could
    0.92
     possibly
    0.91
    maybe
    0.91
     perhaps
    0.89
    might
    0.89
    may
    0.84
     Maybe
    0.82
    Act Density 0.400%

    No Known Activations