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

    Neuronpedia

    INDEX
    Explanations

    references to sacred or religious terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uitka
    -0.20
    tti
    -0.16
    ephy
    -0.16
    ë°į
    -0.14
    ttl
    -0.14
    kening
    -0.14
    æ¯
    -0.14
    دث
    -0.14
    奴
    -0.14
    fusc
    -0.14
    POSITIVE LOGITS
    ramento
    0.25
    ral
    0.23
    char
    0.21
    ificial
    0.21
    raf
    0.21
    ram
    0.21
    rement
    0.20
    rist
    0.19
    ifice
    0.19
    ilege
    0.18
    Act Density 0.010%

    No Known Activations