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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating close relationships or connections

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "closely."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chaser
    -0.79
    ICAN
    -0.76
     Lightning
    -0.71
     Bucket
    -0.70
    å£
    -0.69
    æĹ
    -0.67
    XL
    -0.67
    tein
    -0.66
    çĭ
    -0.65
    Ott
    -0.64
    POSITIVE LOGITS
     closely
    0.94
     aligned
    0.91
     scrutin
    0.89
     enough
    0.87
     resembles
    0.86
     akin
    0.85
     regulated
    0.80
     intertwined
    0.79
     resembled
    0.78
     guarded
    0.78
    Act Density 0.005%

    No Known Activations