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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences or patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adden
    -0.17
    missible
    -0.15
    aug
    -0.14
    stile
    -0.14
    476
    -0.14
    la
    -0.14
     varying
    -0.14
    951
    -0.14
    ahan
    -0.13
    ç´
    -0.13
    POSITIVE LOGITS
    arsity
    0.17
    adolu
    0.15
    aram
    0.15
    sou
    0.14
    asiswa
    0.14
     Sou
    0.14
    ickle
    0.14
     Riv
    0.13
    عا
    0.13
    .zone
    0.13
    Act Density 0.002%

    No Known Activations