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

    Neuronpedia

    INDEX
    Explanations

    paths to files or directories in a software code environment

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and file paths related to software or digital environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.88
     Seym
    -0.71
     choked
    -0.69
     undermin
    -0.69
     judging
    -0.68
     devastated
    -0.68
     defy
    -0.68
    theless
    -0.67
     fracture
    -0.66
     insult
    -0.66
    POSITIVE LOGITS
    AppData
    1.04
    bryce
    0.89
    Windows
    0.89
    SpaceEngineers
    0.89
    src
    0.85
    temp
    0.84
    Roaming
    0.84
    Documents
    0.83
    packages
    0.82
    features
    0.81
    Act Density 0.010%

    No Known Activations