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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "conjure" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uil
    -0.16
    WER
    -0.15
    ızı
    -0.15
     Cr
    -0.14
    iglia
    -0.14
    ÑģÑĤиÑĩ
    -0.14
    Touches
    -0.13
    ÙĨØ´
    -0.13
    trak
    -0.13
    ió
    -0.13
    POSITIVE LOGITS
    olly
    0.22
    unt
    0.20
    oint
    0.19
     conj
    0.19
    oints
    0.18
    ektiv
    0.18
    unct
    0.17
    uration
    0.17
    ural
    0.17
    untos
    0.16
    Act Density 0.013%

    No Known Activations