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

    Neuronpedia

    INDEX
    Explanations

    instances of connecting phrases like 'and'

    oai_token-act-pair · gpt-3.5-turbo

    repetitive conjunctions that suggest a list or continuation of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atan
    -0.78
    emi
    -0.75
     Powered
    -0.72
    DX
    -0.71
    busters
    -0.69
    spect
    -0.69
    BuyableInstoreAndOnline
    -0.68
    uta
    -0.68
    ibble
    -0.68
    ahime
    -0.67
    POSITIVE LOGITS
     consequently
    1.54
     furthermore
    1.50
     thus
    1.39
     hence
    1.37
     moreover
    1.35
     therefore
    1.30
     thereby
    1.26
     vice
    1.25
     secondly
    1.17
     thence
    1.16
    Act Density 0.240%

    No Known Activations