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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time periods and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.14
    ÄĽÅ¾
    -0.14
    _least
    -0.14
    emachine
    -0.14
    füh
    -0.14
    slu
    -0.14
    ième
    -0.13
    -uppercase
    -0.13
    inheritDoc
    -0.13
    robe
    -0.13
    POSITIVE LOGITS
     span
    0.80
    Span
    0.55
    span
    0.55
     spans
    0.53
     Span
    0.52
    -span
    0.50
    _span
    0.43
    (span
    0.41
     space
    0.40
    .span
    0.37
    Act Density 0.099%

    No Known Activations