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

    Neuronpedia

    INDEX
    Explanations

    references to literature

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fty
    -0.64
    addafi
    -0.64
     twitch
    -0.63
     Maurit
    -0.62
    ebus
    -0.61
    por
    -0.60
    ermanent
    -0.59
    heed
    -0.57
    adjust
    -0.57
     Gry
    -0.56
    POSITIVE LOGITS
     literature
    0.88
    emis
    0.80
    istry
    0.79
    DragonMagazine
    0.75
    geist
    0.74
     RELE
    0.72
     writ
    0.71
    cox
    0.70
    uggest
    0.69
    wallet
    0.68
    Act Density 0.021%

    No Known Activations