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

    Neuronpedia

    INDEX
    Explanations

    phrases related to repeated actions or sequences of events

    oai_token-act-pair · gpt-3.5-turbo

    patterns of repetition and redundancy in actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Thumbnail
    -0.85
    arton
    -0.70
    erville
    -0.70
    allery
    -0.67
    uci
    -0.66
    orthy
    -0.66
    ogun
    -0.66
    士
    -0.66
    ahime
    -0.66
    qualified
    -0.65
    POSITIVE LOGITS
     Eventually
    1.34
     until
    1.32
    until
    1.25
     endlessly
    1.24
     till
    1.24
     alternating
    1.21
    Eventually
    1.20
     futile
    1.09
     incess
    1.08
     repetition
    1.06
    Act Density 0.603%

    No Known Activations