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

    Neuronpedia

    INDEX
    Explanations

    the contraction " 's "

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the contraction "there's."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rence
    -0.74
    ller
    -0.70
    roit
    -0.67
    \/
    -0.63
    velop
    -0.62
    stal
    -0.61
    IENT
    -0.61
    Wars
    -0.61
    shire
    -0.61
    Initialized
    -0.59
    POSITIVE LOGITS
     gotta
    1.27
     gonna
    1.10
     been
    0.94
     got
    0.88
     Been
    0.74
     going
    0.71
    etsk
    0.70
     gotten
    0.68
    ometimes
    0.68
    been
    0.68
    Act Density 0.036%

    No Known Activations