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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms wrapped in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    phrases enclosed in quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     afar
    -0.91
     upon
    -0.79
     preceded
    -0.78
     merely
    -0.77
     mim
    -0.76
     summar
    -0.75
     elsewhere
    -0.75
     within
    -0.74
     mirrors
    -0.74
     simply
    -0.74
    POSITIVE LOGITS
    Golden
    1.45
    ultimate
    1.43
    worst
    1.41
    classic
    1.35
    little
    1.33
    dark
    1.33
    big
    1.33
    anti
    1.32
    gold
    1.31
    great
    1.31
    Act Density 0.076%

    No Known Activations