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

    Neuronpedia

    INDEX
    Explanations

    quantitative and evaluative terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ercul
    -0.18
    ead
    -0.17
    ábado
    -0.17
     position
    -0.17
    edo
    -0.16
    udget
    -0.16
    anou
    -0.15
     Daniels
    -0.14
    apan
    -0.14
    edm
    -0.14
    POSITIVE LOGITS
    339
    0.16
    (named
    0.14
    uality
    0.13
    599
    0.13
     predatory
    0.13
    راÙĨÛĮ
    0.13
     Guth
    0.13
    417
    0.13
     Starr
    0.13
    uggling
    0.12
    Act Density 0.037%

    No Known Activations