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

    Neuronpedia

    INDEX
    Explanations

    phrases describing things as extraordinary or exceptional

    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
    epend
    -0.83
    pai
    -0.79
    ©¶æ
    -0.75
    enser
    -0.71
    eter
    -0.71
    avis
    -0.70
    arians
    -0.70
    vere
    -0.70
    adle
    -0.69
    nery
    -0.68
    POSITIVE LOGITS
    NESS
    0.88
     amazing
    0.80
     incredible
    0.76
     feat
    0.76
     amounts
    0.76
     feats
    0.74
     rendition
    0.73
     lengths
    0.72
     coincidence
    0.72
     talent
    0.71
    Act Density 0.025%

    No Known Activations