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

    Neuronpedia

    INDEX
    Explanations

    phrases related to debatable or contrasting viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.86
    hart
    -0.73
    igr
    -0.73
    enei
    -0.71
    ":-
    -0.69
    ciples
    -0.68
    cture
    -0.68
    arthed
    -0.68
    interstitial
    -0.66
    oused
    -0.66
    POSITIVE LOGITS
     rightfully
    1.26
     indeed
    1.19
     rightly
    1.17
     doubtless
    1.10
     yes
    1.09
     hence
    1.08
     possibly
    1.08
     vice
    1.06
     presumably
    1.05
     maybe
    1.05
    Act Density 0.142%

    No Known Activations