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

    Neuronpedia

    INDEX
    Explanations

    time-related descriptors indicating the timing of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    early and late events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hende
    -0.45
     czarne
    -0.41
    orianCalendar
    -0.40
     ciento
    -0.39
     vœ
    -0.35
     cuer
    -0.34
    évaluateur
    -0.34
     enfans
    -0.34
    lampa
    -0.33
     moks
    -0.33
    POSITIVE LOGITS
    early
    1.02
    Early
    0.97
     early
    0.96
     EARLY
    0.88
    EARLY
    0.86
     Early
    0.85
     frühen
    0.82
    帖最后由
    0.73
    late
    0.73
    fjspx
    0.73
    Act Density 0.009%

    No Known Activations