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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols like '»' and some specific patterns

    oai_token-act-pair · gpt-3.5-turbo

    special characters and punctuation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gers
    -0.80
    nings
    -0.76
    viron
    -0.75
    chnology
    -0.75
    tto
    -0.73
    ctions
    -0.73
    zona
    -0.69
    crow
    -0.67
    vern
    -0.66
    ndra
    -0.66
    POSITIVE LOGITS
    ÑĮ
    0.93
    ial
    0.80
    alon
    0.78
    orrow
    0.76
    issions
    0.74
    ipl
    0.73
    åĭ
    0.73
    oan
    0.71
    rypt
    0.70
    ican
    0.70
    Act Density 0.010%

    No Known Activations