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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate transitions or changes in context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     the
    -0.60
     no
    -0.54
     not
    -0.53
     certainly
    -0.53
     none
    -0.52
     truly
    -0.52
     neither
    -0.49
     yes
    -0.49
     mâ
    -0.48
    certainly
    -0.48
    POSITIVE LOGITS
    bootstrapcdn
    0.88
    OGND
    0.85
    кож
    0.82
     ویکی‌پدیای
    0.80
     виправивши
    0.75
    "");
    0.75
    mapStateToProps
    0.74
    LabelTagHelper
    0.73
    IndentedString
    0.73
    )_/¯
    0.72
    Act Density 0.005%

    No Known Activations