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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticism or negative judgment

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors, particularly related to criticism or derogatory terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gow
    -0.79
    minster
    -0.73
     laun
    -0.65
    abre
    -0.65
     Gardens
    -0.64
    united
    -0.64
    anmar
    -0.64
    bnb
    -0.63
    quartered
    -0.61
     purch
    -0.61
    POSITIVE LOGITS
    alion
    0.90
    ction
    0.84
    ible
    0.80
    dden
    0.72
    chio
    0.71
    iment
    0.67
    ilet
    0.66
    ype
    0.65
    fusc
    0.65
    ione
    0.65
    Act Density 0.042%

    No Known Activations