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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or exclusions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "except."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mary
    -0.68
    yrs
    -0.66
    venture
    -0.65
    pt
    -0.63
    hetamine
    -0.62
    foreseen
    -0.61
    election
    -0.61
    gged
    -0.60
    ãĤ¿
    -0.60
    rounder
    -0.60
    POSITIVE LOGITS
    ional
    1.14
     insofar
    0.81
    ords
    0.74
     Zucker
    0.73
    arus
    0.72
    icut
    0.65
    livious
    0.65
    ions
    0.65
    inarily
    0.63
    MENTS
    0.63
    Act Density 0.021%

    No Known Activations