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

    Neuronpedia

    INDEX
    Explanations

    patterns of denial and justification in discussions

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

    Following certain words or phrases

    np_acts-logits-general · gemini-2.0-flash

    negation or denial

    np_acts-logits-general · gemini-2.5-flash-lite

    language that denies or minimizes responsibility or wrongdoing—refuting connections, claiming coincidence, or expressing skeptical/ironic dismissal.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.82
    +#+#
    -0.66
    ftagPool
    -0.65
    ConstraintMaker
    -0.60
    OGND
    -0.58
     estekak
    -0.58
    BeginContext
    -0.57
     kaarangay
    -0.57
    tagext
    -0.57
     pinulongan
    -0.56
    POSITIVE LOGITS
    eek
    0.39
    yargs
    0.39
     Ingram
    0.37
     البر
    0.37
     denied
    0.37
    def
    0.36
    denied
    0.36
     interest
    0.35
     def
    0.35
    liege
    0.34
    Act Density 0.318%

    No Known Activations