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

    Neuronpedia

    INDEX
    Explanations

    words related to negative connotations or derogatory terms

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "slang" or derogatory terms

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

    words that begin with "sl"

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Negative Logits
    ICAN
    -0.69
     concess
    -0.68
     recomm
    -0.61
     conclud
    -0.61
     cessation
    -0.61
     waiver
    -0.61
     hereafter
    -0.60
    ciation
    -0.60
    ä¸ī
    -0.60
    alty
    -0.59
    POSITIVE LOGITS
    ishly
    0.83
    buck
    0.81
    odan
    0.81
    atism
    0.79
    puff
    0.75
    cheon
    0.71
    dog
    0.71
    ppe
    0.70
    ords
    0.69
    grass
    0.68
    Act Density 0.117%

    No Known Activations