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

    Neuronpedia

    INDEX
    Explanations

    mentions of authorities and formal processes in a context that discusses legal or regulatory matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fallback
    -0.15
     Fellowship
    -0.14
     faint
    -0.14
    ì§Ŀ
    -0.14
     Federation
    -0.13
     Fortune
    -0.13
    fad
    -0.13
     predecessor
    -0.13
    [first
    -0.13
     Fletcher
    -0.13
    POSITIVE LOGITS
     final
    0.93
    final
    0.79
     Final
    0.69
    -final
    0.68
    (final
    0.67
    Final
    0.65
     FINAL
    0.65
     finally
    0.63
    _final
    0.63
    .final
    0.63
    Act Density 0.110%

    No Known Activations