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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.16
     çĶ°
    -0.16
    itele
    -0.15
    ules
    -0.15
    ard
    -0.14
    ary
    -0.14
    284
    -0.14
    xffffffff
    -0.14
     Cricket
    -0.13
    465
    -0.13
    POSITIVE LOGITS
    edom
    0.15
    çĥŃ
    0.15
    SizePolicy
    0.15
    ewan
    0.15
    olan
    0.15
    ERVE
    0.14
    íħĶ
    0.14
    ettle
    0.14
    çĨ±
    0.14
    ÑĢеÑĤ
    0.14
    Act Density 0.002%

    No Known Activations