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

    Neuronpedia

    INDEX
    Explanations

    elements related to character transformations and supernatural abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.56
    ;-)
    -0.54
    ✨:
    -0.53
    ahhh
    -0.51
    :-)
    -0.51
    ❤️❤️❤️
    -0.50
     ❤️❤️
    -0.50
    -0.50
     !!!!
    -0.50
     ♥️
    -0.50
    POSITIVE LOGITS
    MfG
    0.64
     aswell
    0.59
     ибо
    0.52
     peores
    0.51
     IIRC
    0.51
    ██
    0.51
     Auft
    0.50
     ingame
    0.49
    伱
    0.49
     Debido
    0.48
    Act Density 1.265%

    No Known Activations