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

    Neuronpedia

    INDEX
    Explanations

    words related to legal terminology and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     auffi
    -0.88
     NSCoder
    -0.83
    RegressionTest
    -0.82
     pleaſure
    -0.81
    ſelf
    -0.80
    bcryptjs
    -0.79
     uſe
    -0.77
     myſelf
    -0.77
     itſelf
    -0.76
    InitVars
    -0.73
    POSITIVE LOGITS
    ia
    1.03
    io
    0.94
    ias
    0.92
    ian
    0.91
    IAN
    0.85
    ios
    0.85
    IA
    0.84
     ia
    0.77
    ium
    0.74
    ial
    0.74
    Act Density 2.209%

    No Known Activations