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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of artistic expression and creativity, particularly in relation to media, storytelling, and music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    θεν
    -0.15
    _OCCURRED
    -0.14
    ixel
    -0.14
    onne
    -0.14
    âĢ¦)↵↵
    -0.14
    ynchronously
    -0.14
    /tos
    -0.14
    ãģ£ãģį
    -0.14
     лиÑĪÑĮ
    -0.14
    ãĤĪãĤĬãĤĤ
    -0.14
    POSITIVE LOGITS
     is
    0.41
     has
    0.31
     will
    0.30
     was
    0.28
     can
    0.28
     would
    0.25
     seems
    0.25
     becomes
    0.24
     could
    0.23
     should
    0.23
    Act Density 1.097%

    No Known Activations