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

    Neuronpedia

    INDEX
    Explanations

    contractions of "is"

    oai_token-act-pair · gpt-3.5-turbo

    repeated uses of the contraction "he's" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zes
    -0.66
    izes
    -0.65
    iew
    -0.63
    rence
    -0.60
    irm
    -0.60
    terior
    -0.60
    uple
    -0.60
     Result
    -0.59
    ization
    -0.58
    oint
    -0.58
    POSITIVE LOGITS
     gotta
    1.37
    been
    1.30
     gonna
    1.28
     been
    1.24
     got
    1.21
     gotten
    1.19
     gone
    0.94
     Been
    0.92
     supposed
    0.89
     going
    0.81
    Act Density 0.080%

    No Known Activations