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

    Neuronpedia

    INDEX
    Explanations

    narratives and interactions involving personal relationships and emotional expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    self
    -0.52
    R
    -0.45
    Injectable
    -0.43
    H
    -0.42
    ir
    -0.41
    T
    -0.40
    ↵
    -0.39
    addGap
    -0.37
    optic
    -0.37
    M
    -0.37
    POSITIVE LOGITS
     CreateTagHelper
    0.87
    AsUp
    0.82
    antMatchers
    0.72
    🏻‍♀️
    0.71
    fony
    0.70
    таратура
    0.70
    webElementGuid
    0.68
    KommentareTeilen
    0.67
    isNameExpr
    0.65
     Himo
    0.65
    Act Density 0.174%

    No Known Activations