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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal representations of byte sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vol
    -0.16
    озна
    -0.14
    imers
    -0.14
    ylie
    -0.14
    elon
    -0.14
     dads
    -0.14
     neutral
    -0.14
    aña
    -0.14
    inger
    -0.14
    ìĤ´
    -0.14
    POSITIVE LOGITS
    orman
    0.14
    itaire
    0.14
    umbo
    0.14
    bang
    0.13
    ANNER
    0.13
     Dix
    0.13
    adÃŃ
    0.13
     Britann
    0.13
    opro
    0.13
    xBD
    0.13
    Act Density 0.006%

    No Known Activations