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

    Neuronpedia

    INDEX
    Explanations

    references to time, events, or specific historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozem
    -0.17
    ncy
    -0.16
    orta
    -0.16
     skoro
    -0.16
    ufs
    -0.15
    reserve
    -0.15
    alette
    -0.15
     dostan
    -0.14
    empor
    -0.14
    orks
    -0.14
    POSITIVE LOGITS
     countdown
    0.18
     suo
    0.18
    los
    0.17
     Countdown
    0.16
     mismo
    0.16
    uso
    0.16
     same
    0.15
     sole
    0.15
    lo
    0.15
    ibo
    0.15
    Act Density 0.020%

    No Known Activations