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

    Neuronpedia

    INDEX
    Explanations

    the word "Was" at the beginning of sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "was."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resonance
    -0.68
    eering
    -0.67
    atories
    -0.66
    rouse
    -0.66
    otic
    -0.64
    objects
    -0.61
     rites
    -0.61
    Footnote
    -0.61
    ranean
    -0.60
    ouver
    -0.59
    POSITIVE LOGITS
    nt
    0.94
    peria
    0.88
    iago
    0.80
    terness
    0.78
    BuyableInstoreAndOnline
    0.78
    hers
    0.77
    nit
    0.76
     Wrong
    0.75
    wolves
    0.75
    ihad
    0.74
    Act Density 0.008%

    No Known Activations