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

    Neuronpedia

    INDEX
    Explanations

    security-related terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.94
    kson
    -0.78
    hes
    -0.77
    ICA
    -0.76
    oline
    -0.71
    sembly
    -0.70
    phrine
    -0.69
    zl
    -0.68
    liam
    -0.68
    igible
    -0.68
    POSITIVE LOGITS
     breaches
    0.94
    policy
    0.91
     vulnerabilities
    0.90
     flaws
    0.85
     enhancements
    0.84
     checkpoints
    0.82
     protocols
    0.81
     breach
    0.81
     checkpoint
    0.80
     sandbox
    0.79
    Act Density 0.032%

    No Known Activations