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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters that are not meaningful text

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.84
    esses
    -0.76
    zeb
    -0.75
    ppelin
    -0.74
    urally
    -0.73
    enhagen
    -0.72
    verbs
    -0.71
    bably
    -0.71
    cients
    -0.70
    ependence
    -0.69
    POSITIVE LOGITS
    dayName
    0.84
    ////////////////////////////////
    0.73
    CLASSIFIED
    0.71
    ÃĹ
    0.71
    catentry
    0.69
    naire
    0.68
    Wide
    0.67
    âĨij
    0.67
    Upload
    0.65
    ItemTracker
    0.64
    Act Density 0.013%

    No Known Activations