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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their usage in context

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

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.72
    MessageTagHelper
    -0.71
    DockStyle
    -0.69
    ArrowToggle
    -0.63
    UrlResolution
    -0.59
     kasarigan
    -0.59
     Taktlose
    -0.58
    GEBURTSDATUM
    -0.58
    tvguidetime
    -0.58
     ivelany
    -0.56
    POSITIVE LOGITS
     [
    0.55
     (
    0.54
     recommending
    0.46
     assigning
    0.45
     intervene
    0.45
     assign
    0.44
    [
    0.44
     appoints
    0.44
    siębior
    0.43
     awarding
    0.42
    Act Density 0.114%

    No Known Activations