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

    Neuronpedia

    INDEX
    Explanations

    contractions of "is not"

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating absence or lack

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     towed
    -0.89
     facult
    -0.72
     Jinn
    -0.69
     Powered
    -0.65
     transformed
    -0.65
     doomed
    -0.64
     guided
    -0.64
     Antar
    -0.63
     tricked
    -0.62
     entertained
    -0.62
    POSITIVE LOGITS
    't
    1.13
    dayName
    0.78
    xus
    0.77
    AMY
    0.75
    fore
    0.73
    eway
    0.73
    ileged
    0.72
    nox
    0.71
    advertisement
    0.70
    DEN
    0.70
    Act Density 0.032%

    No Known Activations