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

    Neuronpedia

    INDEX
    Explanations

    descriptive words related to negative judgment or criticism

    oai_token-act-pair · gpt-3.5-turbo

    words related to definitions and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minster
    -0.78
     phased
    -0.60
    ovych
    -0.60
     womb
    -0.60
     bour
    -0.59
     nurs
    -0.59
    soDeliveryDate
    -0.59
     Introduced
    -0.59
    gow
    -0.57
     Trouble
    -0.56
    POSITIVE LOGITS
    alion
    0.82
    ible
    0.79
    fusc
    0.78
    ilet
    0.77
    tein
    0.73
    iencies
    0.72
    ction
    0.72
    ij士
    0.71
    dden
    0.71
    itely
    0.71
    Act Density 0.039%

    No Known Activations