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

    Neuronpedia

    INDEX
    Explanations

    phrases that specify exceptions or exclusions related to costs or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chad
    -0.47
    <eos>
    -0.45
     «
    -0.43
     keber
    -0.42
    lem
    -0.39
     did
    -0.38
     Les
    -0.38
     앞
    -0.38
     round
    -0.38
     vor
    -0.37
    POSITIVE LOGITS
     autorytatywna
    1.03
    msgTypes
    0.98
    webElementXpaths
    0.94
     AssemblyCulture
    0.92
     resourceCulture
    0.86
     ModelExpression
    0.85
    ConstraintMaker
    0.84
    Diweddarwch
    0.83
    UserScript
    0.81
    IntoConstraints
    0.81
    Act Density 0.259%

    No Known Activations