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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "normal" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.68
     kasarigan
    -0.65
    utilisons
    -0.62
     tjän
    -0.61
     gyhoeddwyd
    -0.58
    ForResult
    -0.56
    UnknownFields
    -0.56
     setPassword
    -0.55
    ším
    -0.55
     LoggerFactory
    -0.55
    POSITIVE LOGITS
     NORMAL
    0.99
     normals
    0.95
    ORMAL
    0.93
     Normal
    0.93
    NORMAL
    0.92
    Normal
    0.91
    ormal
    0.89
    normal
    0.87
     normal
    0.86
     Norma
    0.80
    Act Density 0.122%

    No Known Activations