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

    Neuronpedia

    INDEX
    Explanations

    words related to religious practices and objects

    oai_token-act-pair · gpt-3.5-turbo

    specific phonetic patterns or syllables that are common in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.85
    REDACTED
    -0.77
    DragonMagazine
    -0.70
    é»Ĵ
    -0.64
     microwave
    -0.63
    ALLY
    -0.63
    ãģ®éŃĶ
    -0.60
    åħī
    -0.58
    etheless
    -0.58
    issance
    -0.57
    POSITIVE LOGITS
    ghai
    1.01
    bole
    1.00
    puff
    0.91
    len
    0.82
    peg
    0.80
    aun
    0.78
    anski
    0.78
    pe
    0.77
    aker
    0.77
    lee
    0.76
    Act Density 0.049%

    No Known Activations