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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal preferences and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lÃŃ
    -0.16
    ugar
    -0.16
    lat
    -0.15
    ucas
    -0.15
    ernals
    -0.15
    adies
    -0.14
    RING
    -0.14
    ivre
    -0.14
    udging
    -0.14
    lÃŃ
    -0.13
    POSITIVE LOGITS
    eldon
    0.20
    asz
    0.16
    elli
    0.16
    ometown
    0.16
    rix
    0.16
    reeze
    0.15
     Reeves
    0.14
    ikki
    0.14
    .finish
    0.14
    ustos
    0.14
    Act Density 0.408%

    No Known Activations