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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting used in mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Pab
    -0.77
    twimg
    -0.72
     Crick
    -0.66
     <<<<<<<<<<<<<<
    -0.66
    Pab
    -0.66
    RegressionTest
    -0.65
    发表于
    -0.64
     Schna
    -0.62
     nawr
    -0.61
    makeText
    -0.60
    POSITIVE LOGITS
    ~\
    0.70
    TagHelper
    0.68
    registrer
    0.67
    *~*~
    0.65
    WebVitals
    0.65
    ScopeManager
    0.64
     pylint
    0.64
     Quels
    0.63
    eſ
    0.62
     JURIS
    0.62
    Act Density 0.017%

    No Known Activations