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

    Neuronpedia

    INDEX
    Explanations

    references to rules, policies, and legal statutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onica
    -0.18
     Verd
    -0.15
    _traits
    -0.15
     spell
    -0.14
    iky
    -0.14
    asses
    -0.14
    cona
    -0.13
    Traits
    -0.13
    ĸ
    -0.13
    asse
    -0.13
    POSITIVE LOGITS
     violations
    0.24
     violation
    0.24
     violated
    0.23
     honored
    0.22
     Viol
    0.21
     viol
    0.20
    Violation
    0.20
     honoured
    0.19
    -viol
    0.19
    Applied
    0.19
    Act Density 0.199%

    No Known Activations