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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated vowels or consonants

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of vowel sequences or elongated expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.75
     Redux
    -0.71
     Prospect
    -0.68
     Runner
    -0.65
    crime
    -0.64
    oidal
    -0.64
     Pav
    -0.64
     Tsarnaev
    -0.61
    nikov
    -0.61
     Pers
    -0.60
    POSITIVE LOGITS
    ooo
    1.10
    aaaa
    0.96
    mmmm
    0.91
    oooo
    0.90
    AAA
    0.89
    mmm
    0.89
    !!!!!
    0.85
    aaa
    0.84
    ffee
    0.83
    =]
    0.82
    Act Density 0.027%

    No Known Activations