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

    Neuronpedia

    INDEX
    Explanations

    exclamatory words emphasizing positive qualities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of amazement or admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pai
    -0.88
    epend
    -0.85
    avis
    -0.78
    few
    -0.78
    eter
    -0.77
    aper
    -0.74
    ppo
    -0.74
    embed
    -0.73
    vere
    -0.73
    eper
    -0.71
    POSITIVE LOGITS
     rendition
    0.93
     feats
    0.87
    NESS
    0.86
     feat
    0.82
     accomplishment
    0.78
     coincidence
    0.77
     amounts
    0.77
     sounding
    0.74
     teamwork
    0.72
     talent
    0.72
    Act Density 0.039%

    No Known Activations