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

    Neuronpedia

    INDEX
    Explanations

    terms related to a large, significant majority or agreement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a strong majority or predominance in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    psons
    -0.72
    tein
    -0.72
    thur
    -0.68
    Afee
    -0.66
    href
    -0.66
    esty
    -0.64
     Straw
    -0.63
    fol
    -0.62
     Redemption
    -0.61
    anth
    -0.61
    POSITIVE LOGITS
     reliant
    0.90
     comprised
    0.85
     populated
    0.78
     favoring
    0.78
     dominated
    0.78
     represented
    0.75
     concentrated
    0.75
     disadvantage
    0.74
     relying
    0.74
     populate
    0.72
    Act Density 0.022%

    No Known Activations