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

    Neuronpedia

    INDEX
    Explanations

    negations and their context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    are
    -0.67
     Groves
    -0.67
    gasus
    -0.66
    op
    -0.66
     cartes
    -0.63
     dragen
    -0.63
    OP
    -0.61
     Lev
    -0.61
     является
    -0.61
     Goodman
    -0.60
    POSITIVE LOGITS
     useAppContext
    1.06
     pleaſure
    1.01
    "])
    1.01
     raiſ
    1.01
     purpoſe
    1.00
     Anſ
    0.98
     iſt
    0.97
    }))
    0.95
     faſt
    0.95
     dreamstime
    0.93
    Act Density 0.147%

    No Known Activations