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

    Neuronpedia

    INDEX
    Explanations

    words related to positive aspects or actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and inquiries about individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QUIRE
    -0.65
    asonable
    -0.61
     compr
    -0.60
     accumulating
    -0.60
     suspic
    -0.58
     describ
    -0.58
    vantage
    -0.58
    olutions
    -0.57
     awa
    -0.57
    anyon
    -0.56
    POSITIVE LOGITS
    soDeliveryDate
    0.75
    fal
    0.72
    ãģ£
    0.69
     Cind
    0.63
    ãĥ¬
    0.62
     Sphere
    0.61
     congr
    0.60
    )'
    0.60
    itars
    0.59
    cussion
    0.58
    Act Density 0.422%

    No Known Activations