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

    Neuronpedia

    INDEX
    Explanations

    expressions of evaluation or judgment about quality or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quite
    -0.29
     probably
    -0.27
     Quite
    -0.25
     Probably
    -0.24
    probably
    -0.23
     almost
    -0.22
     pretty
    -0.20
    quite
    -0.20
     rất
    -0.20
    almost
    -0.19
    POSITIVE LOGITS
     slightest
    0.30
     ANY
    0.29
     yoksa
    0.28
    anything
    0.26
     anything
    0.26
     вдÑĢÑĥг
    0.25
     anywhere
    0.25
     EVER
    0.24
     nÃło
    0.23
     truly
    0.23
    Act Density 0.420%

    No Known Activations