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

    Neuronpedia

    INDEX
    Explanations

    terms associated with legal or moral violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awtextra
    -0.78
    informatics
    -0.71
     ISNI
    -0.69
     worauf
    -0.68
    Архівовано
    -0.64
     proxy
    -0.61
     golf
    -0.60
     Resili
    -0.60
    Gus
    -0.58
     сре
    -0.58
    POSITIVE LOGITS
     violation
    1.32
     violations
    1.29
     violate
    1.24
     violating
    1.23
     violated
    1.21
     Violation
    1.18
    violation
    1.16
     Violations
    1.16
     violates
    1.12
     Viol
    1.11
    Act Density 0.075%

    No Known Activations