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

    Neuronpedia

    INDEX
    Explanations

    instances where specific characters or symbols appear in succession

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating the end of statements or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neighb
    -0.77
     kettle
    -0.71
     cabbage
    -0.69
     feared
    -0.67
     resisted
    -0.66
     clock
    -0.66
     brut
    -0.64
     board
    -0.64
     scen
    -0.64
    ellery
    -0.63
    POSITIVE LOGITS
     Retrieved
    0.94
     Accessed
    0.88
    aspx
    0.84
    illin
    0.79
    mobi
    0.77
    wcsstore
    0.76
    wav
    0.74
    jpg
    0.73
    zip
    0.73
    IGHTS
    0.72
    Act Density 0.063%

    No Known Activations