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

    Neuronpedia

    INDEX
    Explanations

    references to capability or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.76
    XmlAccessorType
    -0.62
    OGND
    -0.56
    WithIOException
    -0.55
     cấp
    -0.55
    être
    -0.52
     correctes
    -0.50
    CppMethod
    -0.50
    WarningLevel
    -0.49
    فات
    -0.49
    POSITIVE LOGITS
     expect
    0.98
     always
    0.96
     certainly
    0.77
     bet
    0.76
     probably
    0.71
    always
    0.71
     trust
    0.68
     imagine
    0.66
     also
    0.66
     choose
    0.66
    Act Density 0.184%

    No Known Activations