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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of 'ON' in the texts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ON" and its variations, indicating a focus on online content or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erous
    -0.65
    ile
    -0.60
     eleg
    -0.57
    usting
    -0.56
     conversions
    -0.55
    iles
    -0.55
     gent
    -0.55
    oler
    -0.53
    iler
    -0.52
    mpeg
    -0.52
    POSITIVE LOGITS
     ON
    3.37
     OFF
    1.61
     IN
    1.57
     TO
    1.40
     UP
    1.38
    ONS
    1.36
     FROM
    1.36
     INTO
    1.33
     OF
    1.32
    ON
    1.31
    Act Density 0.012%

    No Known Activations