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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing pride or admiration towards something or someone

    oai_token-act-pair · gpt-3.5-turbo

    expressions of pride

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     modes
    -0.73
    resistant
    -0.68
     cess
    -0.67
     phased
    -0.67
     drafts
    -0.65
     directions
    -0.65
     downward
    -0.64
     ET
    -0.63
     accelerator
    -0.63
    problem
    -0.62
    POSITIVE LOGITS
    clus
    0.81
     accomplishment
    0.81
    ¥µ
    0.78
    76561
    0.77
     Marketable
    0.75
    ¥
    0.74
     ç¥ŀ
    0.74
     Magical
    0.73
     congratulate
    0.69
     accomplishments
    0.68
    Act Density 0.066%

    No Known Activations