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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "except" or "exception"

    np_acts-logits-general · gemini-2.0-flash

    except for or exception of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.75
     auffi
    -0.69
     Cras
    -0.66
     uſed
    -0.65
     crdi
    -0.63
     ROK
    -0.63
     Hanno
    -0.61
     AppModule
    -0.61
     ſhe
    -0.60
     Majefty
    -0.60
    POSITIVE LOGITS
     maybe
    0.87
     perhaps
    0.81
     Maybe
    0.65
    maybe
    0.63
     except
    0.63
     occasional
    0.63
     those
    0.63
    getActiveSheet
    0.61
     the
    0.61
     occasionally
    0.59
    Act Density 0.132%

    No Known Activations