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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and syntax-related tokens in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pie
    -0.16
    ima
    -0.15
    INCLUDED
    -0.14
     arter
    -0.14
    IMA
    -0.14
    uber
    -0.14
     Goth
    -0.14
    ÑĦÑĦ
    -0.14
    otton
    -0.14
    ouver
    -0.13
    POSITIVE LOGITS
    /Dk
    0.17
    iosa
    0.16
     Sole
    0.16
    elik
    0.16
    zes
    0.16
    ÑĥÑĤ
    0.15
    oje
    0.15
    uiten
    0.14
     Gravity
    0.14
    aab
    0.14
    Act Density 0.004%

    No Known Activations