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

    Neuronpedia

    INDEX
    Explanations

    mentions of challenges or struggles

    oai_token-act-pair · gpt-3.5-turbo

    the character "Ļ" occurring with high frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     successes
    -0.68
     sensational
    -0.66
     pressures
    -0.66
     puff
    -0.64
     advantages
    -0.63
     rudimentary
    -0.63
     decimal
    -0.63
     leaps
    -0.63
     misunder
    -0.62
     paperback
    -0.62
    POSITIVE LOGITS
    ï¸ı
    1.28
    ï¸
    0.98
    ¯¯
    0.90
    gypt
    0.90
    worthiness
    0.85
    Balt
    0.82
    uth
    0.81
    sure
    0.80
    conom
    0.78
    ski
    0.78
    Act Density 0.445%

    No Known Activations