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

    Neuronpedia

    INDEX
    Explanations

    elements related to character traits and personality descriptions

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

    grilling Clinton

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Douglas
    -0.35
     proposé
    -0.34
     colspan
    -0.34
    Following
    -0.32
     proposée
    -0.32
    Until
    -0.32
    The
    -0.32
    addPreferredGap
    -0.32
    Altern
    -0.31
     Bedarf
    -0.31
    POSITIVE LOGITS
    TypedDataSet
    0.78
    contentLoaded
    0.67
    expandindo
    0.66
     ویکی‌پدیا
    0.63
     Мексичка
    0.62
    gonic
    0.60
     unknownFields
    0.57
     kasarigan
    0.57
    Geplaatst
    0.57
     plufieurs
    0.55
    Act Density 0.033%

    No Known Activations