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

    Neuronpedia

    INDEX
    Explanations

    mentions of female characters and their actions within the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    γά
    -0.14
    è²Į
    -0.14
    imler
    -0.14
     ìĿ´ëĬĶ
    -0.14
    огÑĥ
    -0.14
    ierz
    -0.13
     моÑı
    -0.13
     мо
    -0.13
     mio
    -0.13
    ç»ĻæĪij
    -0.13
    POSITIVE LOGITS
     maybe
    0.20
     Mary
    0.20
     God
    0.19
     really
    0.18
     ...
    0.18
     Jesus
    0.17
     Maybe
    0.17
    Decoration
    0.16
     things
    0.16
     sometimes
    0.16
    Act Density 0.000%

    No Known Activations