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

    Neuronpedia

    INDEX
    Explanations

    terms related to honor and recognition

    oai_token-act-pair · gpt-3.5-turbo

    references to honor and related terms or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _>
    -0.73
    arre
    -0.70
     Ange
    -0.67
    hesive
    -0.63
    roads
    -0.63
     Lans
    -0.63
    sen
    -0.61
    tered
    -0.60
    sample
    -0.60
    arten
    -0.59
    POSITIVE LOGITS
    ific
    1.27
    ably
    1.16
    itism
    0.88
     honored
    0.84
    abilia
    0.83
     honoured
    0.82
     bestowed
    0.82
     honors
    0.82
    ABLE
    0.80
    ificial
    0.79
    Act Density 0.050%

    No Known Activations