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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social validation and the desire to impress others

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

    seeking approval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createSlice
    -0.45
    XtraEditors
    -0.41
    INSEE
    -0.37
     ReactDOM
    -0.37
     uVar
    -0.37
    WebElementEntity
    -0.35
     Laure
    -0.35
    ngdoc
    -0.32
    unknownFields
    -0.32
     ModelExpression
    -0.32
    POSITIVE LOGITS
     auprès
    0.50
    IsMutable
    0.49
    bootstrapcdn
    0.49
    TintMode
    0.47
    Cringe
    0.45
     competitiveness
    0.44
    Tikang
    0.44
     OMITBAD
    0.44
    ыгана
    0.42
    ValueStyle
    0.42
    Act Density 0.023%

    No Known Activations