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

    Neuronpedia

    INDEX
    Explanations

    periods and punctuation marks, indicating sentence endings or pauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erties
    -0.16
    aso
    -0.16
    ави
    -0.16
    avo
    -0.14
    andi
    -0.14
    etin
    -0.14
    oss
    -0.14
    ò
    -0.13
     Hag
    -0.13
    eness
    -0.13
    POSITIVE LOGITS
    .deg
    0.16
    ñana
    0.15
    vero
    0.15
    ndern
    0.14
    isia
    0.14
    /Peak
    0.14
    armed
    0.14
    hol
    0.14
    alley
    0.13
    ÑĪев
    0.13
    Act Density 0.038%

    No Known Activations