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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or limitation in knowledge

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to uncertainty and impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.97
    PE
    -0.70
     Appears
    -0.68
    scenes
    -0.66
    faces
    -0.64
    rawdownloadcloneembedreportprint
    -0.63
    grave
    -0.63
    fired
    -0.62
    SourceFile
    -0.61
    plates
    -0.61
    POSITIVE LOGITS
     reliably
    1.26
     quantify
    1.24
     predict
    1.24
     definitively
    1.20
     accurately
    1.19
     know
    1.18
     determine
    1.18
     ascertain
    1.16
     gauge
    1.15
     distinguish
    1.09
    Act Density 0.197%

    No Known Activations