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

    Neuronpedia

    INDEX
    Explanations

    references to legal terms and violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.46
    threshold
    -0.45
    stretchr
    -0.44
    MemoryWarning
    -0.43
     threshold
    -0.41
    Portail
    -0.41
    /*
    -0.40
    JoinTable
    -0.40
     authorities
    -0.39
    CORS
    -0.39
    POSITIVE LOGITS
     violation
    0.79
     illegal
    0.77
     dist
    0.77
     violations
    0.75
     Illegal
    0.71
     Violation
    0.71
    Illegal
    0.68
    illegal
    0.68
     distortion
    0.66
     violate
    0.66
    Act Density 0.094%

    No Known Activations