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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating repetition or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    och
    -0.17
     Twice
    -0.16
    ÌĤ
    -0.15
    ister
    -0.15
    rell
    -0.14
    ISTER
    -0.14
    635
    -0.14
    ìĹ
    -0.13
     Nova
    -0.13
     кли
    -0.13
    POSITIVE LOGITS
    bai
    0.21
    Å¡en
    0.16
    aeper
    0.16
    à¹Ģหล
    0.16
    pio
    0.15
    .ease
    0.15
    SION
    0.15
    ÑĪиб
    0.15
    hai
    0.15
    oval
    0.15
    Act Density 0.155%

    No Known Activations