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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exploration or thematic depth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymm
    -0.16
    ãn
    -0.16
     cann
    -0.16
    lap
    -0.15
    ÑģÑĤан
    -0.14
    ledon
    -0.14
    avor
    -0.14
     CascadeType
    -0.14
     flag
    -0.14
    ved
    -0.14
    POSITIVE LOGITS
    irma
    0.17
    roje
    0.14
     Kür
    0.14
    Fant
    0.14
    fds
    0.14
    æ¶
    0.14
    fad
    0.14
    agher
    0.13
     Resolver
    0.13
     Yönetim
    0.13
    Act Density 0.159%

    No Known Activations