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

    Neuronpedia

    INDEX
    Explanations

    the word "while" and related temporal conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.65
     resourceCulture
    -0.59
    ſelf
    -0.56
    ReusableCell
    -0.55
    الحياه
    -0.54
    KommentareTeilen
    -0.54
     itſelf
    -0.51
    ੝
    -0.50
     dieux
    -0.47
    --}}
    -0.47
    POSITIVE LOGITS
     during
    0.69
     when
    0.68
     because
    0.59
     regardless
    0.59
     after
    0.58
     whenever
    0.57
     while
    0.54
     despite
    0.52
     but
    0.52
     without
    0.51
    Act Density 0.356%

    No Known Activations