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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rankings or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Siz
    -0.18
     Bes
    -0.15
    ingles
    -0.15
    yster
    -0.14
    oud
    -0.14
     Ebony
    -0.14
    bes
    -0.14
    cheme
    -0.14
     Kis
    -0.14
    714
    -0.14
    POSITIVE LOGITS
     ten
    0.20
     five
    0.19
    eldorf
    0.15
    ायल
    0.15
     Ten
    0.15
     reasons
    0.14
    alian
    0.14
    asons
    0.14
     деÑģÑı
    0.14
    ults
    0.14
    Act Density 0.022%

    No Known Activations