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

    Neuronpedia

    INDEX
    Explanations

    past tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acco
    -0.16
    åĬ±
    -0.15
    erved
    -0.14
    arel
    -0.14
    ãĥªãĤ¹
    -0.14
    ãģ¾ãģ¾
    -0.13
    lier
    -0.13
     bod
    -0.13
    adius
    -0.13
     leds
    -0.13
    POSITIVE LOGITS
     instrumental
    0.29
     charged
    0.28
     tasked
    0.24
     retained
    0.23
     called
    0.23
     charge
    0.23
    instrument
    0.23
     key
    0.22
     responsible
    0.22
     integral
    0.22
    Act Density 0.250%

    No Known Activations