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

    Neuronpedia

    INDEX
    Explanations

    hesitation sounds or filler words

    oai_token-act-pair · gpt-3.5-turbo

    filler words and verbal hesitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Constructed
    -0.65
    BOOK
    -0.65
    Flight
    -0.63
    STDOUT
    -0.63
    Preview
    -0.62
    女
    -0.59
    avers
    -0.58
    æĪ¦
    -0.58
    IAL
    -0.58
    eting
    -0.58
    POSITIVE LOGITS
    mmm
    0.97
    rah
    0.92
    pty
    0.88
    ihara
    0.88
     huh
    0.84
    ahah
    0.84
    mmmm
    0.80
    selves
    0.77
    rella
    0.75
    agine
    0.73
    Act Density 0.036%

    No Known Activations