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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aur
    -0.19
    azu
    -0.15
    xic
    -0.15
    efs
    -0.14
    793
    -0.14
    ICODE
    -0.13
     Escorts
    -0.13
    ersen
    -0.13
    792
    -0.13
    994
    -0.13
    POSITIVE LOGITS
    eselect
    0.15
    eno
    0.15
    Ả
    0.15
    ucer
    0.15
    ãĤĴãģĭ
    0.14
    ún
    0.14
    ouser
    0.14
    .opens
    0.13
    ofil
    0.13
     Wagner
    0.13
    Act Density 0.012%

    No Known Activations