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

    Neuronpedia

    INDEX
    Explanations

    pronouns that indicate the speaker's identity or involvement in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olland
    -0.15
    arena
    -0.14
    cene
    -0.14
    arna
    -0.14
     Interracial
    -0.13
    ัà¸Ļม
    -0.13
    .Formatter
    -0.13
    graphic
    -0.13
    vised
    -0.13
    .MixedReality
    -0.13
    POSITIVE LOGITS
    ãĥģãĥ¥
    0.16
    rtle
    0.15
    sembl
    0.14
    athing
    0.14
    atan
    0.14
    adow
    0.14
    eries
    0.14
    vp
    0.14
    eto
    0.14
    semblies
    0.14
    Act Density 0.109%

    No Known Activations