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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to proof, evidence, and hypothesis testing in academic or argumentative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.72
    ">//
    -0.65
     ModelExpression
    -0.63
    ftagPool
    -0.55
    ScopeManager
    -0.54
    ſelves
    -0.54
    AndEndTag
    -0.53
     AssemblyCulture
    -0.52
    Autoritní
    -0.51
    ItemBackground
    -0.50
    POSITIVE LOGITS
     prove
    0.85
     proving
    0.85
     proves
    0.81
     prouver
    0.78
     Prove
    0.78
     Proving
    0.73
    Prove
    0.73
     verify
    0.71
     beweisen
    0.71
     verifies
    0.71
    Act Density 0.936%

    No Known Activations