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

    Neuronpedia

    INDEX
    Explanations

    references to technical implementations or workarounds for software issues

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    >{@
    -0.57
     للمعارف
    -0.51
     asse
    -0.50
     boiler
    -0.47
    yargs
    -0.46
    翘
    -0.45
    RSpec
    -0.45
    Boiler
    -0.45
    CppMethod
    -0.43
    thansa
    -0.43
    POSITIVE LOGITS
    &&&&
    0.81
     rapp
    0.77
     workaround
    0.77
     Strickland
    0.74
    Filmography
    0.74
    surate
    0.72
     contentType
    0.71
    tramp
    0.70
     makeStyles
    0.69
     bruises
    0.69
    Act Density 0.049%

    No Known Activations