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

    Neuronpedia

    INDEX
    Explanations

    words related to computer systems

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "systems" and related technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĢ
    -0.79
    tein
    -0.75
    liest
    -0.74
    odder
    -0.69
    ãĥĥ
    -0.68
     earnest
    -0.67
    pull
    -0.66
    FLAG
    -0.65
    gg
    -0.65
    Bone
    -0.64
    POSITIVE LOGITS
     systems
    1.35
     architectures
    1.02
    etting
    1.00
     system
    0.96
     integ
    0.93
    etter
    0.85
    afety
    0.85
     implementations
    0.84
     configurations
    0.83
    ystem
    0.82
    Act Density 0.024%

    No Known Activations