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

    Neuronpedia

    INDEX
    Explanations

    contractions of "is" followed by a description or action

    oai_token-act-pair · gpt-3.5-turbo

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

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Result
    -0.65
    iew
    -0.64
    TAIN
    -0.63
    itial
    -0.61
    irm
    -0.60
    DS
    -0.60
    ={
    -0.60
    aneous
    -0.59
    velop
    -0.59
     Deaths
    -0.58
    POSITIVE LOGITS
     gotta
    1.29
     gonna
    1.25
    been
    1.14
     been
    1.11
     got
    1.08
     gotten
    1.05
     gone
    0.86
     supposed
    0.85
     going
    0.82
     Been
    0.82
    Act Density 0.087%

    No Known Activations