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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and emotional vulnerability

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     kepad
    -0.52
     Germans
    -0.48
    љу
    -0.47
     udaler
    -0.47
     disambiguazione
    -0.46
    啶
    -0.45
    elux
    -0.45
     poudre
    -0.44
    ghijkl
    -0.44
     AssemblyTitle
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.87
     للاسماء
    0.75
    MigrationBuilder
    0.68
    tagext
    0.67
    CreateMap
    0.66
     CreateTagHelper
    0.65
     invokingState
    0.61
     يتيمه
    0.60
    󠁮
    0.59
    WEBPACK
    0.59
    Act Density 0.025%

    No Known Activations