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

    Neuronpedia

    INDEX
    Explanations

    praise and admiration for others

    oai_token-act-pair · gpt-3.5-turbo

    positive evaluations of individuals, particularly in the context of sports or teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HuffPost
    -0.76
     Partial
    -0.76
    Reuters
    -0.72
    unal
    -0.71
    iatus
    -0.70
     Worse
    -0.69
    olla
    -0.69
    udging
    -0.68
    Wars
    -0.68
    OPA
    -0.68
    POSITIVE LOGITS
     terrific
    1.26
     unbelievable
    1.18
     phenomenal
    1.18
     talented
    1.14
     fantastic
    1.10
     versatile
    1.10
     underrated
    1.09
     versatility
    1.04
     talent
    1.04
     toughness
    1.04
    Act Density 0.366%

    No Known Activations