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

    Neuronpedia

    INDEX
    Explanations

    linguistic markers associated with emotional expression and emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.16
    ular
    -0.15
    foundland
    -0.14
     Giang
    -0.14
    ascar
    -0.14
    agon
    -0.14
    ilder
    -0.14
    ãģıãĤīãģĦ
    -0.14
    екÑĥ
    -0.14
    chwitz
    -0.14
    POSITIVE LOGITS
    uers
    0.15
     world
    0.14
    oric
    0.14
    دا
    0.14
    uman
    0.14
    aben
    0.14
    own
    0.13
    دÙĩ
    0.13
    TouchEvent
    0.13
    zman
    0.13
    Act Density 0.001%

    No Known Activations