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

    Neuronpedia

    INDEX
    Explanations

    contractions with an apostrophe

    oai_token-act-pair · gpt-3.5-turbo

    the use of single quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.74
    avorite
    -0.74
    âĹ¼
    -0.73
    igslist
    -0.72
    nown
    -0.70
     Izan
    -0.70
     destro
    -0.70
     ..............
    -0.67
     Archdemon
    -0.66
     lapse
    -0.63
    POSITIVE LOGITS
    til
    1.20
    cause
    1.18
    Interstitial
    1.08
     ',
    1.07
    -'
    1.06
    tis
    1.05
    neath
    1.03
    Mech
    1.00
    taboola
    0.96
    no
    0.94
    Act Density 0.034%

    No Known Activations