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

    Neuronpedia

    INDEX
    Explanations

    special text characters, potentially related to coding or formatting

    oai_token-act-pair · gpt-3.5-turbo

    numerical sequences or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esses
    -0.87
    xual
    -0.86
    verbs
    -0.79
    iences
    -0.76
    ependence
    -0.74
    urally
    -0.73
    ppelin
    -0.73
    perse
    -0.69
    etimes
    -0.69
    itably
    -0.69
    POSITIVE LOGITS
    dayName
    0.73
    CLASSIFIED
    0.73
    ////////////////////////////////
    0.72
    Upload
    0.71
    ÃĹ
    0.70
    FIELD
    0.69
    mare
    0.69
    Wide
    0.68
    LAB
    0.68
    naire
    0.68
    Act Density 0.019%

    No Known Activations