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

    Neuronpedia

    INDEX
    Explanations

    references to workshops or classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shit
    -0.17
    tring
    -0.17
     seul
    -0.16
    rew
    -0.16
    recated
    -0.16
    son
    -0.16
    .fromString
    -0.15
    reme
    -0.15
    ve
    -0.15
    ocene
    -0.15
    POSITIVE LOGITS
    curity
    0.21
    quence
    0.19
    -ÑĤо
    0.16
     beiden
    0.16
    cond
    0.16
    ìłĢ
    0.15
    æĿŁ
    0.14
    SEMB
    0.14
    itel
    0.14
    emiah
    0.14
    Act Density 0.106%

    No Known Activations