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

    Neuronpedia

    INDEX
    Explanations

    phrases describing alignment, matching, or coincidence between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to correspondence or alignment between concepts or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chat
    -0.60
    zan
    -0.59
    æµ
    -0.59
    ËĪ
    -0.59
    ond
    -0.58
    worms
    -0.57
     hunted
    -0.56
     recomm
    -0.56
     beware
    -0.56
    abouts
    -0.55
    POSITIVE LOGITS
     nicely
    1.11
     neatly
    1.02
     closely
    0.92
     perfectly
    0.90
     sharply
    0.86
     squarely
    0.80
     favorably
    0.78
     stark
    0.76
    Against
    0.74
     poorly
    0.72
    Act Density 0.187%

    No Known Activations