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

    Neuronpedia

    INDEX
    Explanations

    references to storytelling or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovich
    -0.17
    ir
    -0.14
    teness
    -0.14
    (PR
    -0.14
    Ãłi
    -0.14
    rog
    -0.14
    ãĥ¥
    -0.14
    евиÑĩ
    -0.13
    rogate
    -0.13
    ------+------+
    -0.13
    POSITIVE LOGITS
     story
    0.56
     Story
    0.48
     stories
    0.46
    story
    0.45
    Story
    0.44
     tale
    0.42
     STORY
    0.40
    _story
    0.40
     Stories
    0.40
    -story
    0.38
    Act Density 0.034%

    No Known Activations