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

    Neuronpedia

    INDEX
    Explanations

    references to evidence and proof related to claims or theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IPA
    -0.14
    ftware
    -0.13
    632
    -0.13
    486
    -0.13
     ApplicationException
    -0.13
    λÏī
    -0.13
    /umd
    -0.13
    627
    -0.13
    595
    -0.13
    feld
    -0.12
    POSITIVE LOGITS
     evidence
    0.78
     Evidence
    0.64
    Evidence
    0.59
     proof
    0.57
     evid
    0.48
    vidence
    0.47
     Proof
    0.45
    proof
    0.43
    Proof
    0.42
     proofs
    0.38
    Act Density 0.342%

    No Known Activations