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

    Neuronpedia

    INDEX
    Explanations

    important concepts or factors related to a discussion or narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aire
    -0.14
    ÅĻÃŃz
    -0.14
    aklı
    -0.14
    umble
    -0.14
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.14
    achs
    -0.13
    ÙĤÙĤ
    -0.13
     fur
    -0.13
    ftware
    -0.13
     Shapiro
    -0.13
    POSITIVE LOGITS
    hole
    0.21
    notes
    0.18
    ì¶ķ
    0.16
    /key
    0.15
    /core
    0.15
    holes
    0.15
    POINTS
    0.15
    chains
    0.15
    ILLED
    0.15
    logger
    0.15
    Act Density 0.015%

    No Known Activations