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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "on" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ――――――――
    -0.92
     fVar
    -0.81
    luigi
    -0.80
    BibitemShut
    -0.79
     vectorielles
    -0.77
     ―――――
    -0.77
    adecimal
    -0.77
     authentique
    -0.75
    liani
    -0.73
     SEDS
    -0.73
    POSITIVE LOGITS
     On
    1.75
    On
    1.62
     ON
    1.53
     on
    1.29
    on
    1.26
    setOn
    1.25
    isOn
    1.17
    ON
    1.17
    addOn
    1.13
    mOn
    1.11
    Act Density 0.101%

    No Known Activations