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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ż
    -0.15
     coordinate
    -0.14
    åª
    -0.14
    elsey
    -0.14
    ince
    -0.14
    cas
    -0.13
    ç«ł
    -0.13
    lemen
    -0.13
    bed
    -0.13
    laus
    -0.13
    POSITIVE LOGITS
     again
    0.24
     for
    0.20
    again
    0.20
    sgiving
    0.20
     Again
    0.17
     goodness
    0.17
     bunch
    0.16
     heavens
    0.16
     much
    0.16
    fully
    0.16
    Act Density 0.012%

    No Known Activations