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

    Neuronpedia

    INDEX
    Explanations

    programming language and framework-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.83
    UrlResolution
    -0.76
    SourceChecksum
    -0.72
    TagMode
    -0.71
    BeginContext
    -0.71
    RegressionTest
    -0.69
     &___
    -0.68
    hasMoreElements
    -0.66
    msgTypes
    -0.64
     *)__
    -0.64
    POSITIVE LOGITS
     itſelf
    0.83
     houſe
    0.74
     OCS
    0.73
     Majefty
    0.71
    UserScript
    0.71
     pleaſure
    0.71
     NBS
    0.71
     afp
    0.69
     QP
    0.68
     triton
    0.68
    Act Density 0.020%

    No Known Activations