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

    Neuronpedia

    INDEX
    Explanations

    prepositions, specifically 'to'

    oai_token-act-pair · gpt-3.5-turbo

    instances of threats or dangers to various entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hent
    -0.75
    tions
    -0.71
    soDeliveryDate
    -0.68
    leys
    -0.62
    erred
    -0.60
    iHUD
    -0.60
     handled
    -0.60
     updated
    -0.59
    ror
    -0.59
    need
    -0.58
    POSITIVE LOGITS
    tnc
    0.79
     humankind
    0.78
     injure
    0.77
    efficiency
    0.74
    wered
    0.74
     Flavoring
    0.74
     mankind
    0.73
    asted
    0.72
     conserve
    0.71
    asts
    0.71
    Act Density 0.120%

    No Known Activations