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

    Neuronpedia

    INDEX
    Explanations

    word starting with an apostrophe

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the apostrophe character used in contractions or possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Archdemon
    -0.85
     ..............
    -0.67
     Hendricks
    -0.66
     Vaugh
    -0.65
     Ames
    -0.64
     printer
    -0.63
     Izan
    -0.63
     polyg
    -0.63
     Leilan
    -0.62
     Argon
    -0.61
    POSITIVE LOGITS
    cause
    1.44
    til
    1.36
    Interstitial
    1.31
    Mech
    1.20
    tis
    1.20
    taboola
    1.11
    Cause
    1.04
    keeper
    0.97
    -'
    0.97
    round
    0.96
    Act Density 0.050%

    No Known Activations