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

    Neuronpedia

    INDEX
    Explanations

    contractions with 't

    oai_token-act-pair · gpt-3.5-turbo

    negative statements about inability or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amer
    -0.68
     Appears
    -0.68
    imity
    -0.66
    soType
    -0.66
    ItemImage
    -0.63
    interstitial
    -0.60
    bard
    -0.60
    estate
    -0.59
    heavy
    -0.58
    DragonMagazine
    -0.58
    POSITIVE LOGITS
     afford
    1.00
     necessarily
    0.95
     imagine
    0.85
    icably
    0.84
     stomach
    0.81
     tolerate
    0.80
    urtles
    0.79
     bother
    0.79
    icable
    0.78
     seem
    0.77
    Act Density 0.023%

    No Known Activations