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

    Neuronpedia

    INDEX
    Explanations

    instances of evidence or proof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /umd
    -0.16
    ë²Ī
    -0.15
    lek
    -0.15
    andro
    -0.14
    595
    -0.14
    lesai
    -0.14
    _DIGEST
    -0.14
    ÛĮدÙĨ
    -0.13
     defaultMessage
    -0.13
    olis
    -0.13
    POSITIVE LOGITS
     evidence
    0.94
     Evidence
    0.79
    Evidence
    0.73
     proof
    0.64
    vidence
    0.56
     evid
    0.56
     Proof
    0.51
    proof
    0.48
    Proof
    0.47
    è¯ģ
    0.45
    Act Density 0.325%

    No Known Activations