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

    Neuronpedia

    INDEX
    Explanations

    technical formatting elements within text

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.72
     insult
    -0.72
     step
    -0.71
     stricken
    -0.67
     choked
    -0.67
     defy
    -0.64
     leap
    -0.64
     judging
    -0.64
     contender
    -0.64
     devastated
    -0.63
    POSITIVE LOGITS
    AppData
    1.06
    SpaceEngineers
    0.97
    Roaming
    0.90
    Documents
    0.87
    addons
    0.87
    bryce
    0.86
    Content
    0.85
    scripts
    0.82
    76561
    0.80
    packages
    0.80
    Act Density 0.008%

    No Known Activations