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

    Neuronpedia

    INDEX
    Explanations

    characters and relationships in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiba
    -0.15
    اÙģÙĬ
    -0.15
    Haunted
    -0.15
    xea
    -0.14
    ãĤ¤ãĥ³ãĥĪ
    -0.14
    stral
    -0.14
    ront
    -0.14
    otel
    -0.14
    stit
    -0.14
    ì´Į
    -0.14
    POSITIVE LOGITS
     rewind
    0.16
     Kear
    0.15
    icia
    0.15
     accompanying
    0.14
     hav
    0.13
    Ñı
    0.13
     overhead
    0.13
    ara
    0.13
    icket
    0.13
     Introduced
    0.13
    Act Density 0.058%

    No Known Activations