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

    Neuronpedia

    INDEX
    Explanations

    references to actions or intentions involving "you" and "I"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.88
     Suivez
    -0.81
     Inscrivez
    -0.80
    aguya
    -0.79
     polaire
    -0.75
    jects
    -0.75
    frastructure
    -0.72
     pleaf
    -0.72
    ITERATURE
    -0.72
     Gabor
    -0.71
    POSITIVE LOGITS
    parsedMessage
    0.87
    UnusedPrivate
    0.73
    CppMethod
    0.72
     that
    0.69
    SourceChecksum
    0.68
    interopRequire
    0.66
    adpleegd
    0.66
     ComVisible
    0.66
    aarrggbb
    0.66
    fjspx
    0.65
    Act Density 0.211%

    No Known Activations