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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    大åħ¨
    -0.17
    ÙĪر
    -0.16
    çħ
    -0.15
    é¡
    -0.15
     mist
    -0.15
    丸
    -0.14
    vsp
    -0.14
     Learned
    -0.14
    plits
    -0.14
    upertino
    -0.14
    POSITIVE LOGITS
    ладÑĥ
    0.15
    istrovstvÃŃ
    0.15
    ael
    0.14
    ẫn
    0.14
     Bans
    0.14
    itz
    0.14
    .neo
    0.14
     Tep
    0.13
    ãĥ©ãĥ³ãĥī
    0.13
    arih
    0.13
    Act Density 0.000%

    No Known Activations