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

    Neuronpedia

    INDEX
    Explanations

    references to different pronouns and their usage in context

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

    pronouns followed by modal or auxiliary verbs expressing capability or potential action.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.50
     للاسماء
    -0.50
    новништво
    -0.46
    WriteBarrier
    -0.45
     виправивши
    -0.45
    CHAFT
    -0.41
     tartalomajánló
    -0.40
    UseVisualStyle
    -0.39
    лактика
    -0.39
     مشارکت‌کنندگان
    -0.36
    POSITIVE LOGITS
     own
    0.62
     sendiri
    0.59
     knows
    0.56
     believes
    0.54
     know
    0.54
     heard
    0.53
     believe
    0.52
    ScopeManager
    0.51
     KNOW
    0.49
    ParallelGroup
    0.48
    Act Density 0.344%

    No Known Activations