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

    Neuronpedia

    INDEX
    Explanations

    contractions with an apostrophe followed by the verb "to be"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the contraction "that's."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ievers
    -0.71
    sters
    -0.68
    erers
    -0.67
    ieves
    -0.66
    riors
    -0.64
    nesses
    -0.64
    ling
    -0.63
    icip
    -0.62
    prov
    -0.61
    dylib
    -0.59
    POSITIVE LOGITS
     gonna
    1.08
     gotta
    1.06
     been
    0.76
    SPONSORED
    0.72
     basically
    0.71
     got
    0.70
     alright
    0.70
     Mahjong
    0.70
     why
    0.70
    otta
    0.69
    Act Density 0.051%

    No Known Activations