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

    Neuronpedia

    INDEX
    Explanations

    specific characters, symbols, and citations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically parentheses and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neighb
    -0.79
    ifying
    -0.71
    bye
    -0.70
    dra
    -0.69
     scen
    -0.68
     Nanto
    -0.68
    enta
    -0.64
     describ
    -0.64
     administr
    -0.63
    bucks
    -0.63
    POSITIVE LOGITS
     Retrieved
    0.79
    zip
    0.75
    ,,,,,,,,
    0.73
    ĸļ
    0.70
    wcsstore
    0.69
    reated
    0.68
    cipline
    0.67
    pas
    0.66
    ãħĭãħĭ
    0.66
    =/
    0.65
    Act Density 0.057%

    No Known Activations