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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal proceedings and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vapors
    -0.77
    HEAST
    -0.73
    хьтан
    -0.69
     ComVisible
    -0.65
    تقاوى
    -0.64
    DropColumn
    -0.63
    stdafx
    -0.59
    dafx
    -0.59
     autorytatywna
    -0.59
     Chwiliwch
    -0.59
    POSITIVE LOGITS
     Gauteng
    1.05
     Pretoria
    0.97
     Afrikaans
    0.90
     lekker
    0.89
     Johannesburg
    0.88
     Durban
    0.86
    🇿
    0.84
    initialise
    0.84
    Pty
    0.81
     Cape
    0.81
    Act Density 0.266%

    No Known Activations