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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts, indicating connections or additions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è»
    -0.70
    icro
    -0.69
    igr
    -0.69
    SourceFile
    -0.68
    hart
    -0.68
    ahime
    -0.68
    ciples
    -0.67
    oused
    -0.67
    enei
    -0.67
    acas
    -0.65
    POSITIVE LOGITS
     rightfully
    1.16
     indeed
    1.13
     rightly
    1.11
     doubtless
    1.10
     yes
    1.06
     presumably
    1.04
     maybe
    1.03
     hence
    1.03
     possibly
    1.02
     vice
    1.00
    Act Density 0.139%

    No Known Activations