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

    Neuronpedia

    INDEX
    Explanations

    references to capitals and cities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    %">
    -0.64
    >--}}
    -0.58
    addCriterion
    -0.57
    ---*/
    -0.57
    achusetts
    -0.56
    TypedDataSet
    -0.54
    UserScript
    -0.54
    apimachinery
    -0.53
    InputTagHelper
    -0.53
     AspNetCore
    -0.50
    POSITIVE LOGITS
     Hauptstadt
    0.75
     capitale
    0.69
    اصمة
    0.67
    PerformLayout
    0.66
     cipolla
    0.65
    reht
    0.63
     huvud
    0.63
     authority
    0.60
    yarnpkg
    0.60
     Cathedral
    0.59
    Act Density 0.009%

    No Known Activations