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

    Neuronpedia

    INDEX
    Explanations

    computer-related terms or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to computers and related technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    METHOD
    -0.77
     Redemption
    -0.72
    bringer
    -0.72
     mete
    -0.70
    ModLoader
    -0.68
    abouts
    -0.68
    eca
    -0.67
    fin
    -0.67
    uberty
    -0.65
     Pact
    -0.64
    POSITIVE LOGITS
    puters
    0.89
     readable
    0.87
     computers
    0.86
     hardware
    0.83
     RAID
    0.82
     terminals
    0.81
     laptop
    0.79
     desktop
    0.79
     monitor
    0.78
    ono
    0.76
    Act Density 0.033%

    No Known Activations