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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements in written language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheon
    -0.16
    Ậ
    -0.15
    kos
    -0.14
    vis
    -0.14
    rzy
    -0.14
    addy
    -0.14
     çĭ
    -0.14
    Station
    -0.14
     Station
    -0.14
     station
    -0.14
    POSITIVE LOGITS
     Qed
    0.25
     tactic
    0.25
     Tactics
    0.24
     tactics
    0.23
     Proof
    0.21
    Proof
    0.21
     Nat
    0.21
     proof
    0.21
    Qed
    0.20
     induction
    0.20
    Act Density 0.002%

    No Known Activations