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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing strong criticism or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dec," likely indicating references to declarations or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -1.01
    ansas
    -0.81
    DragonMagazine
    -0.76
    akeru
    -0.75
    culosis
    -0.75
     Archdemon
    -0.70
     Dragonbound
    -0.70
     Graveyard
    -0.67
    finder
    -0.67
    WAYS
    -0.67
    POSITIVE LOGITS
    rypted
    1.40
    ryption
    1.25
    oded
    1.24
    ried
    1.12
    ibel
    1.07
    oder
    1.04
    ently
    1.03
    isions
    1.02
    rypt
    0.97
    ribed
    0.95
    Act Density 0.008%

    No Known Activations