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

    Neuronpedia

    INDEX
    Explanations

    mentions of something being honorable

    oai_token-act-pair · gpt-3.5-turbo

    terms related to honorable mentions and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aum
    -0.83
    reth
    -0.82
    icion
    -0.80
    anas
    -0.78
    etter
    -0.77
    eters
    -0.77
    romy
    -0.71
    Na
    -0.71
    rait
    -0.70
    othe
    -0.69
    POSITIVE LOGITS
    nesses
    0.93
    Magikarp
    0.84
    orable
    0.80
    NESS
    0.74
     applause
    0.68
    ness
    0.67
    justice
    0.66
     Skies
    0.63
     honorable
    0.63
    ABLE
    0.62
    Act Density 0.024%

    No Known Activations