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

    Neuronpedia

    INDEX
    Explanations

    phrases related to privacy policies and user data visibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.89
    SharedDtor
    -0.77
    CppCodeGen
    -0.68
    ismet
    -0.63
     ProtoMessage
    -0.61
    Converters
    -0.58
     postponement
    -0.58
     فريبيس
    -0.56
    Handlung
    -0.55
     prophylactic
    -0.55
    POSITIVE LOGITS
     access
    0.87
     accessible
    0.86
    access
    0.79
    accessible
    0.76
    Accessible
    0.74
     accessed
    0.74
     accessibility
    0.73
     accessibles
    0.72
     visibility
    0.71
     Accessible
    0.69
    Act Density 0.490%

    No Known Activations