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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "except"

    oai_token-act-pair · gpt-3.5-turbo

    the word "except" and its variations, indicating exclusions or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¿
    -0.65
    aimon
    -0.62
     Flavoring
    -0.61
    cent
    -0.60
    hetamine
    -0.59
    idered
    -0.58
    Äĩ
    -0.58
    pt
    -0.57
    itiz
    -0.57
     contag
    -0.56
    POSITIVE LOGITS
    ional
    1.26
    arus
    0.79
    ords
    0.76
    ¯
    0.76
     insofar
    0.72
    icut
    0.71
    livious
    0.67
    ions
    0.67
    ing
    0.67
    ments
    0.66
    Act Density 0.027%

    No Known Activations