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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing positive or commendable qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.18
    astreet
    -0.15
    rosse
    -0.14
    agna
    -0.14
    æľį
    -0.14
    оÑĢоÑĤ
    -0.14
    hor
    -0.14
    oly
    -0.14
    ç¥ŀ
    -0.13
     Marc
    -0.13
    POSITIVE LOGITS
    Wunused
    0.16
    oval
    0.16
    utz
    0.16
    Cancelable
    0.15
    .ISupportInitialize
    0.14
    esk
    0.14
     Ãļ
    0.14
    caf
    0.14
    è¡Ĩ
    0.13
    noop
    0.13
    Act Density 0.051%

    No Known Activations