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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consequences and results, often in a formal or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wine
    -0.15
    jad
    -0.15
    SF
    -0.15
     Kat
    -0.14
    ipop
    -0.14
    omit
    -0.14
     Kata
    -0.14
    fusion
    -0.14
    оза
    -0.14
    /am
    -0.13
    POSITIVE LOGITS
    istrovstvÃŃ
    0.17
    _semaphore
    0.15
    iki
    0.15
    dbl
    0.15
    æĨ¶
    0.15
    ácil
    0.15
    oupon
    0.14
    ytut
    0.14
     mans
    0.14
    imd
    0.14
    Act Density 0.055%

    No Known Activations