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

    Neuronpedia

    INDEX
    Explanations

    references to computers or 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
    -0.86
    uality
    -0.82
    sweet
    -0.76
    uds
    -0.72
    abouts
    -0.71
    reek
    -0.70
    ï¸ı
    -0.66
    eous
    -0.65
    ead
    -0.64
    sym
    -0.64
    POSITIVE LOGITS
     terminals
    0.89
     interfaces
    0.81
     readable
    0.79
    ized
    0.78
     computers
    0.78
    sonian
    0.78
    generated
    0.78
     screens
    0.77
    eers
    0.77
    puters
    0.77
    Act Density 0.037%

    No Known Activations