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

    Neuronpedia

    INDEX
    Explanations

    expressions of admiration or commendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yll
    -0.16
    ̣
    -0.15
    .Rad
    -0.15
    ay
    -0.14
    opsis
    -0.14
    oy
    -0.14
     Äijá»iji
    -0.14
    usted
    -0.14
    roy
    -0.14
    nez
    -0.13
    POSITIVE LOGITS
    ably
    0.25
    able
    0.20
    atory
    0.19
    ovol
    0.18
    eworthy
    0.17
    -worthy
    0.17
    worthy
    0.16
    SSION
    0.15
    fully
    0.15
     ful
    0.15
    Act Density 0.042%

    No Known Activations