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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omics
    -0.76
     millenn
    -0.74
    ŃĶ
    -0.72
     deserved
    -0.72
    lled
    -0.71
     conglomer
    -0.70
     crammed
    -0.69
     impression
    -0.69
    ijing
    -0.69
     mirac
    -0.68
    POSITIVE LOGITS
     Otherwise
    1.75
     Alternatively
    1.74
     Additionally
    1.67
     Depending
    1.63
     Conversely
    1.60
     Likewise
    1.60
     However
    1.58
     Similarly
    1.56
     Therefore
    1.55
     If
    1.55
    Act Density 0.295%

    No Known Activations