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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical proofs and formal arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.79
    ########.
    -0.68
     createSprite
    -0.66
     незавершена
    -0.64
    CloseOperation
    -0.62
    </caption>
    -0.60
     snippetHide
    -0.60
    Diweddarwch
    -0.59
     ExecuteAsync
    -0.58
    λευτα
    -0.56
    POSITIVE LOGITS
    Proof
    0.93
     Proof
    0.89
     PROOF
    0.65
    PROOF
    0.64
     proof
    0.63
    proof
    0.61
     Proofs
    0.60
     Conversely
    0.60
    Conversely
    0.59
    QED
    0.57
    Act Density 0.860%

    No Known Activations