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

    Neuronpedia

    INDEX
    Explanations

    instances of unexpected outcomes or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate an action or event followed by a consequence or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orean
    -0.66
    eur
    -0.64
     Caption
    -0.62
    haw
    -0.62
     Loud
    -0.60
     condol
    -0.60
    favorite
    -0.59
    mot
    -0.58
    oug
    -0.58
    ore
    -0.58
    POSITIVE LOGITS
     remind
    0.87
     reassure
    0.83
    adle
    0.82
     refill
    0.81
     prove
    0.75
     fill
    0.71
     reaff
    0.71
     appease
    0.70
     replen
    0.70
    iety
    0.70
    Act Density 0.056%

    No Known Activations