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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isman
    -0.16
    ergarten
    -0.15
    NI
    -0.15
    PEnd
    -0.14
     acomp
    -0.14
    ISTA
    -0.14
    uzzer
    -0.14
    éħį
    -0.14
     OVERRIDE
    -0.14
    Ñıз
    -0.13
    POSITIVE LOGITS
    pest
    0.15
    chrift
    0.15
    umo
    0.14
    claimer
    0.14
    irst
    0.14
    arti
    0.14
    üstü
    0.14
     Abed
    0.14
    ket
    0.13
    åŁº
    0.13
    Act Density 0.484%

    No Known Activations