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

    Neuronpedia

    INDEX
    Explanations

    expressions related to approval and compliments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĦίοÏħ
    -0.15
    õi
    -0.14
    WithContext
    -0.14
    kers
    -0.14
    ACITY
    -0.14
    vatel
    -0.14
     unsupported
    -0.14
    AGR
    -0.13
    commerce
    -0.13
    yles
    -0.13
    POSITIVE LOGITS
    itters
    0.16
    orex
    0.16
    cheme
    0.15
    234
    0.14
    ırı
    0.14
    436
    0.14
    ä»ĭ
    0.14
    roe
    0.14
    itter
    0.14
    itan
    0.13
    Act Density 0.408%

    No Known Activations