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

    Neuronpedia

    INDEX
    Explanations

    words related to criticism or negative judgment

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to notable individuals and conditions of existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dress
    -0.74
    schild
    -0.68
    loaded
    -0.66
     fertil
    -0.64
    ser
    -0.64
     Leilan
    -0.62
    anwhile
    -0.62
    walking
    -0.62
    xual
    -0.61
     Brom
    -0.61
    POSITIVE LOGITS
    ient
    0.95
    ascript
    0.91
    iencies
    0.78
    ĩ
    0.78
    ishable
    0.77
    ı
    0.77
    isions
    0.76
    awks
    0.75
    ¼
    0.75
    oming
    0.75
    Act Density 0.061%

    No Known Activations