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

    Neuronpedia

    INDEX
    Explanations

    contractions of the verb "to be" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the contraction "we're"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amer
    -0.68
     mater
    -0.67
    andise
    -0.67
    cycl
    -0.67
    odor
    -0.63
    pedia
    -0.62
     separates
    -0.62
     manifests
    -0.60
    shire
    -0.60
    icipated
    -0.60
    POSITIVE LOGITS
     gonna
    1.43
     gotta
    0.91
     going
    0.90
     supposed
    0.86
    etsk
    0.81
     hoping
    0.80
    wolves
    0.80
     lucky
    0.73
     worth
    0.72
     okay
    0.71
    Act Density 0.098%

    No Known Activations