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

    Neuronpedia

    INDEX
    Explanations

    occurrences of mathematical and programming symbols and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NET
    -0.15
     McGr
    -0.15
    aidu
    -0.15
    вÑĸлÑĮ
    -0.15
    loi
    -0.15
     NET
    -0.15
    ëĦ
    -0.14
    ÃĹ↵↵
    -0.14
    kek
    -0.14
     McGregor
    -0.14
    POSITIVE LOGITS
     Nat
    0.30
     nat
    0.28
    Nat
    0.26
    nat
    0.24
     Qed
    0.22
     induction
    0.22
     tactic
    0.22
    _nat
    0.21
     Tactics
    0.21
     destruct
    0.20
    Act Density 0.002%

    No Known Activations