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

    Neuronpedia

    INDEX
    Explanations

    instances of contrast or conjunctions indicating exceptions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eced
    -0.15
    ery
    -0.15
    uries
    -0.14
    actual
    -0.14
    ERY
    -0.14
    ucha
    -0.14
     Sokol
    -0.14
    ettle
    -0.13
    ibal
    -0.13
    Century
    -0.13
    POSITIVE LOGITS
    fern
    0.14
    istro
    0.14
     isNaN
    0.14
    åľ¨çº¿è§Ĥçľĭ
    0.14
    wins
    0.13
    pins
    0.13
    SEQUENTIAL
    0.13
    reta
    0.13
    İ
    0.13
    intl
    0.13
    Act Density 0.038%

    No Known Activations