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

    Neuronpedia

    INDEX
    Explanations

    awards or achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to awards and player recognitions in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orus
    -0.76
    etsk
    -0.74
    rils
    -0.72
    heny
    -0.72
    llah
    -0.70
    ptoms
    -0.69
    uni
    -0.69
    bern
    -0.65
    eria
    -0.64
    zsche
    -0.64
    POSITIVE LOGITS
     sorts
    0.96
     course
    0.78
     Excellence
    0.77
     Champions
    0.75
     Thrones
    0.73
     Conservation
    0.72
    Hon
    0.70
     hers
    0.67
    Measure
    0.66
    ortunately
    0.65
    Act Density 0.155%

    No Known Activations