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

    Neuronpedia

    INDEX
    Explanations

    instances of phrases or words related to ranking and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èª
    -0.14
    gli
    -0.14
    мÑĭ
    -0.14
    sg
    -0.14
    ko
    -0.14
    elian
    -0.14
    ãģĶãģĸ
    -0.14
    ton
    -0.14
    cz
    -0.13
    uent
    -0.13
    POSITIVE LOGITS
    /or
    0.27
    /of
    0.20
    rade
    0.20
     amp
    0.20
    vanced
    0.19
    amp
    0.17
    ipar
    0.15
    REW
    0.15
    rades
    0.14
    AMP
    0.14
    Act Density 0.080%

    No Known Activations