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

    Neuronpedia

    INDEX
    Explanations

    arguments and claims made in legal contexts

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

    argument or arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    期刊论文
    -0.59
    #+#
    -0.57
     AssemblyCulture
    -0.56
     myſelf
    -0.56
    ]")]
    -0.56
    webElementGuid
    -0.55
    featureID
    -0.55
     ſind
    -0.53
     BoxFit
    -0.50
     Numerade
    -0.50
    POSITIVE LOGITS
     argued
    1.23
     argue
    1.23
     arguments
    1.23
     argument
    1.21
     arguing
    1.17
     argues
    1.09
    argument
    1.07
     Argument
    1.06
    Argument
    1.04
     argumento
    1.04
    Act Density 0.087%

    No Known Activations