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

    Neuronpedia

    INDEX
    Explanations

    function definitions and related code structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.91
     يتيمه
    -0.77
    الإنجليزية
    -0.75
     صوتيه
    -0.70
     fallu
    -0.69
     AssemblyCulture
    -0.69
    ⓧ
    -0.69
    pédie
    -0.68
     fuite
    -0.68
    hyrchwyd
    -0.67
    POSITIVE LOGITS
    FontOfSize
    0.49
    <eos>
    0.49
    ضان
    0.48
    isRequired
    0.45
     فريبيس
    0.44
     harte
    0.43
     Felsen
    0.42
    ↵↵
    0.42
     indepen
    0.42
    GeneratedCode
    0.41
    Act Density 0.003%

    No Known Activations