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

    Neuronpedia

    INDEX
    Explanations

    terms related to arguments and argumentative discourse

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

    "argue" or "argument"

    np_acts-logits-general · gemini-2.0-flash

    about arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.90
    Datuak
    -0.89
    expandindo
    -0.82
     jadx
    -0.75
     cerv
    -0.73
    contentLoaded
    -0.70
    Ofic
    -0.69
     Colette
    -0.68
     coron
    -0.66
    帖最后由
    -0.66
    POSITIVE LOGITS
     arguments
    1.26
     Arguments
    1.20
     argue
    1.13
    arguments
    1.10
     ARG
    1.02
     argues
    1.01
    Arguments
    0.98
     argument
    0.97
     argued
    0.94
     Argument
    0.91
    Act Density 0.101%

    No Known Activations