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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the continuation or progression of a story or text

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases indicating continuation or ongoing narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bats
    -0.64
    onom
    -0.63
    haps
    -0.62
    anca
    -0.62
    eco
    -0.59
    ufact
    -0.58
    Honest
    -0.58
    merce
    -0.58
     fame
    -0.57
    heit
    -0.56
    POSITIVE LOGITS
     BELOW
    1.10
     below
    0.95
     Below
    0.92
    below
    0.84
    advertisement
    0.77
     transcript
    0.64
    gallery
    0.63
    scroll
    0.63
    chenko
    0.62
     TBD
    0.62
    Act Density 0.009%

    No Known Activations