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

    Neuronpedia

    INDEX
    Explanations

    expressions of gladness or happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    frau
    -0.16
    er
    -0.16
    etics
    -0.16
    izzo
    -0.15
    677
    -0.15
    werk
    -0.14
    eway
    -0.14
    ansas
    -0.14
    ikki
    -0.13
    à¹Ģà¸Ħ
    -0.13
    POSITIVE LOGITS
    stone
    0.21
    ys
    0.19
    fully
    0.17
    wyn
    0.17
     tid
    0.17
    win
    0.17
    dest
    0.17
    lıkla
    0.16
    indow
    0.16
    stones
    0.16
    Act Density 0.006%

    No Known Activations