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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inability or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auen
    -0.18
    ip
    -0.18
    atch
    -0.16
    818
    -0.16
    allow
    -0.15
    ss
    -0.15
    ed
    -0.14
    bit
    -0.14
    cal
    -0.14
    alt
    -0.14
    POSITIVE LOGITS
    mere
    0.18
    jedn
    0.15
    ift
    0.14
    omik
    0.14
    ë§
    0.14
    ysqli
    0.14
    gow
    0.14
    WXYZ
    0.14
    ÃŃž
    0.14
    IFT
    0.13
    Act Density 0.030%

    No Known Activations