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

    Neuronpedia

    INDEX
    Explanations

    the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SerializedSize
    -0.81
     ModelExpression
    -0.78
     Мексичка
    -0.72
    batore
    -0.70
    gorithm
    -0.69
    ]--;
    -0.66
     وتسجيلات
    -0.65
     resourceCulture
    -0.65
    IONI
    -0.65
    stateProvider
    -0.65
    POSITIVE LOGITS
    on
    3.38
    ON
    2.22
    On
    1.23
    at
    1.00
    onor
    0.98
    upon
    0.97
    onner
    0.90
    onite
    0.88
    オン
    0.85
    onii
    0.84
    Act Density 0.086%

    No Known Activations