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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks like periods and quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence-ending markers, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     depl
    -0.92
     unsus
    -0.84
     indis
    -0.82
     teasp
    -0.82
     conspic
    -0.81
     repud
    -0.80
    Þ
    -0.77
     unamb
    -0.76
     adequately
    -0.76
     grievance
    -0.75
    POSITIVE LOGITS
     Sometimes
    1.52
     Then
    1.49
     Usually
    1.44
     Especially
    1.43
     Luckily
    1.42
     Eventually
    1.42
     Obviously
    1.41
     But
    1.37
     Hopefully
    1.36
     Whereas
    1.35
    Act Density 0.282%

    No Known Activations