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

    Neuronpedia

    INDEX
    Explanations

    JSON or programming-related text patterns

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lik
    -0.71
     sugg
    -0.65
    romeda
    -0.64
     newsp
    -0.63
     certific
    -0.62
     surv
    -0.62
     charm
    -0.61
     pens
    -0.61
     confir
    -0.61
     challeng
    -0.61
    POSITIVE LOGITS
    tesy
    0.89
    english
    0.78
    soType
    0.77
    BuyableInstoreAndOnline
    0.77
    std
    0.77
    acity
    0.74
     "$:/
    0.71
    taboola
    0.71
    arte
    0.70
     ["
    0.69
    Act Density 0.042%

    No Known Activations