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

    Neuronpedia

    INDEX
    Explanations

    phrases related to films and entertainment experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onse
    -0.14
    uhe
    -0.14
    hl
    -0.14
    elige
    -0.14
    ycz
    -0.13
    aset
    -0.13
    дÑı
    -0.13
    aná
    -0.13
     Fram
    -0.13
     Gle
    -0.13
    POSITIVE LOGITS
     hete
    0.17
    624
    0.16
    inaire
    0.16
    SSIP
    0.15
    inkle
    0.15
     exerc
    0.14
    bfd
    0.14
    ëĭ¤
    0.14
    rides
    0.14
    lij
    0.13
    Act Density 0.124%

    No Known Activations