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

    Neuronpedia

    INDEX
    Explanations

    statements involving contrast or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "it" and related queries regarding its referents or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hitting
    -0.73
    uilding
    -0.71
    TT
    -0.71
    ands
    -0.68
     Travels
    -0.68
    soDeliveryDate
    -0.68
    Tam
    -0.66
    umbn
    -0.64
    acca
    -0.64
    TAG
    -0.63
    POSITIVE LOGITS
     admittedly
    0.93
     nonetheless
    0.86
     occasional
    0.85
     otherwise
    0.83
     disagree
    0.83
     retains
    0.81
     nevertheless
    0.81
     differed
    0.81
     slight
    0.81
     persisted
    0.81
    Act Density 0.225%

    No Known Activations