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

    Neuronpedia

    INDEX
    Explanations

    numeric values, potentially related to frequencies or measurements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    TextWatcher
    -0.52
    Isa
    -0.50
     reason
    -0.49
     dia
    -0.48
    alese
    -0.48
    نين
    -0.47
    ing
    -0.46
     Nether
    -0.46
     carried
    -0.46
     pec
    -0.46
    POSITIVE LOGITS
     coupler
    0.96
    دانشنامهٔ
    0.95
    ooker
    0.94
     ligiloj
    0.90
    knapp
    0.90
     חיצוניים
    0.90
    醐
    0.89
    contentLoaded
    0.88
     ***!
    0.83
    #+#
    0.83
    Act Density 0.118%

    No Known Activations