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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yte
    -0.16
    turnstile
    -0.15
    itud
    -0.15
    bote
    -0.15
    ween
    -0.15
    uida
    -0.15
    ABEL
    -0.15
    rose
    -0.15
    úsqueda
    -0.15
    ακ
    -0.14
    POSITIVE LOGITS
    ahan
    0.17
     Thrones
    0.14
    amil
    0.14
    ög
    0.14
    anda
    0.14
    UMB
    0.14
     æĺ
    0.13
    utron
    0.13
    jet
    0.13
     bak
    0.13
    Act Density 0.164%

    No Known Activations