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

    Neuronpedia

    INDEX
    Explanations

    personalized content for newsletters or subscription services

    oai_token-act-pair · gpt-3.5-turbo

    references to the reader or audience in a conversational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suffice
    -0.72
     Canaver
    -0.63
    orient
    -0.59
    ftime
    -0.59
    luster
    -0.58
    esses
    -0.58
    entimes
    -0.57
    ĸļ
    -0.56
     bows
    -0.56
    images
    -0.55
    POSITIVE LOGITS
    're
    1.10
    've
    1.05
    'll
    0.89
    need
    0.79
    'd
    0.77
    RS
    0.75
    tub
    0.74
     need
    0.73
    iku
    0.66
     want
    0.65
    Act Density 0.069%

    No Known Activations