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

    Neuronpedia

    INDEX
    Explanations

    common opening phrases and punctuation used in formal communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĤ¥
    -0.15
    obra
    -0.15
    æ³¥
    -0.14
    _pointer
    -0.14
    eren
    -0.14
    ++]=
    -0.13
     <*>
    -0.13
    _marshall
    -0.13
    :convert
    -0.13
    ÙĪار
    -0.13
    POSITIVE LOGITS
    impan
    0.16
    illet
    0.15
    stad
    0.15
    ttp
    0.15
    hind
    0.15
    åĽ£
    0.14
    adden
    0.14
    ¥IJ
    0.14
    ritch
    0.14
    icket
    0.14
    Act Density 0.002%

    No Known Activations