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

    Neuronpedia

    INDEX
    Explanations

    names and titles of characters in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geh
    -0.17
    feit
    -0.16
     totiž
    -0.15
     поÑħод
    -0.14
    indow
    -0.14
    leurs
    -0.14
    åij¢
    -0.13
    yre
    -0.13
    reso
    -0.13
    utterstock
    -0.13
    POSITIVE LOGITS
    -san
    0.18
    !
    0.17
     please
    0.17
     what
    0.16
     wake
    0.16
    ,↵↵
    0.16
     you
    0.16
    ,↵
    0.15
    iso
    0.15
    ï¼Įä½ł
    0.15
    Act Density 0.127%

    No Known Activations