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

    Neuronpedia

    INDEX
    Explanations

    text separated by certain symbols such as dashes and underscores

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or symbols used to indicate structure in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lling
    -0.67
     nurs
    -0.66
     deliber
    -0.66
     cradle
    -0.62
    ollar
    -0.60
     snowball
    -0.59
    inav
    -0.57
     clipping
    -0.57
     miscarriage
    -0.57
     synerg
    -0.57
    POSITIVE LOGITS
    */
    1.07
    *****
    0.91
     =================================================================
    0.86
    edit
    0.82
     ARTICLE
    0.81
    quote
    0.78
    Requirements
    0.78
    ---
    0.77
    export
    0.77
    -->
    0.76
    Act Density 0.077%

    No Known Activations