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

    Neuronpedia

    INDEX
    Explanations

    computer-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to computers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eca
    -0.85
    uality
    -0.75
    abouts
    -0.75
    uds
    -0.73
    ModLoader
    -0.72
    sweet
    -0.70
    reek
    -0.67
    ï¸ı
    -0.66
    ORS
    -0.65
    eous
    -0.65
    POSITIVE LOGITS
     terminals
    0.86
     interfaces
    0.81
    generated
    0.81
    ized
    0.80
    izes
    0.78
     readable
    0.78
     screens
    0.78
     glitches
    0.77
     keyboard
    0.77
     keyboards
    0.76
    Act Density 0.039%

    No Known Activations