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

    Neuronpedia

    INDEX
    Explanations

    positive expressions of satisfaction or joy

    oai_token-act-pair · gpt-3.5-turbo

    positive expressions of emotion or satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arettes
    -0.71
     trailed
    -0.68
    VERTISEMENT
    -0.65
    hang
    -0.64
    limits
    -0.63
    heat
    -0.63
    uyomi
    -0.63
    rawled
    -0.62
    ngth
    -0.62
    cum
    -0.62
    POSITIVE LOGITS
     fortunate
    0.69
     congratulate
    0.67
    roud
    0.67
    rix
    0.67
    dy
    0.66
    fully
    0.64
     Parish
    0.64
     welcome
    0.63
    Congratulations
    0.62
    wic
    0.62
    Act Density 0.074%

    No Known Activations