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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the initiation of processes or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shapiro
    -0.15
    apia
    -0.15
    imi
    -0.13
    azu
    -0.13
    asil
    -0.13
    ico
    -0.13
    ابت
    -0.13
     Roth
    -0.13
     Acceler
    -0.13
    lich
    -0.13
    POSITIVE LOGITS
    esson
    0.19
    ATO
    0.17
    tti
    0.16
    umpt
    0.16
    vanced
    0.16
    Ñĥж
    0.16
     parte
    0.15
    phans
    0.15
    ONGO
    0.15
    æļ
    0.15
    Act Density 0.073%

    No Known Activations