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

    Neuronpedia

    INDEX
    Explanations

    contractions

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms of "is" used to express statements or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isively
    -0.70
    atively
    -0.68
    lessly
    -0.66
    riors
    -0.66
    ially
    -0.66
    velop
    -0.65
    sters
    -0.64
     resumes
    -0.63
    nesses
    -0.63
    ievers
    -0.63
    POSITIVE LOGITS
     gonna
    1.02
     gotta
    0.98
    IELD
    0.79
     Mahjong
    0.76
     been
    0.75
    pace
    0.73
     Been
    0.70
    ãĤ°
    0.67
    SPONSORED
    0.67
     got
    0.66
    Act Density 0.038%

    No Known Activations