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

    Neuronpedia

    INDEX
    Explanations

    conversational quotes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the contraction "he's"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obo
    -0.69
    eem
    -0.68
     Waste
    -0.68
    awks
    -0.66
    cess
    -0.64
    "}],"
    -0.63
    iox
    -0.63
    osa
    -0.63
    itial
    -0.62
    orks
    -0.61
    POSITIVE LOGITS
     been
    1.74
    been
    1.67
     gotten
    1.63
     got
    1.49
     gotta
    1.33
     undergone
    1.25
     Been
    1.25
     gone
    1.19
     risen
    1.16
     flown
    1.09
    Act Density 0.088%

    No Known Activations