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

    Neuronpedia

    INDEX
    Explanations

    Latin characters and punctuation

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that are not standard text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bris
    -0.89
    vern
    -0.89
    vantage
    -0.88
    agen
    -0.82
    vier
    -0.81
    imore
    -0.81
    osion
    -0.81
    ussian
    -0.80
    ction
    -0.80
    apers
    -0.79
    POSITIVE LOGITS
     namely
    0.93
     Which
    0.82
     whereas
    0.81
     yeah
    0.78
     implying
    0.75
     Granted
    0.74
     secondly
    0.74
     culminating
    0.73
     whence
    0.72
     ********************************
    0.72
    Act Density 0.178%

    No Known Activations