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

    Neuronpedia

    INDEX
    Explanations

    references to conditions and evaluations that claim increased efficacy or success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     invece
    -0.76
     either
    -0.73
    Either
    -0.73
    either
    -0.71
     Either
    -0.71
     simplesmente
    -0.65
     então
    -0.64
     inoltre
    -0.64
     prostu
    -0.62
    simply
    -0.61
    POSITIVE LOGITS
     technically
    1.28
     nominally
    1.13
     admittedly
    1.07
     ostensibly
    1.02
     itſelf
    0.97
     misschien
    0.96
     undoubtedly
    0.95
     theoretically
    0.93
     certes
    0.91
     may
    0.91
    Act Density 0.556%

    No Known Activations