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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms indicating the presence of evidence or claims, particularly in a critical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.73
     "..\..\..\
    -0.69
     resourceCulture
    -0.67
    CodeAttribute
    -0.66
     "..\..\
    -0.65
    -0.64
    EDEFAULT
    -0.63
     estekak
    -0.63
    simpleType
    -0.63
     nahilalakip
    -0.60
    POSITIVE LOGITS
     evidence
    2.43
     proof
    2.36
    evidence
    2.12
     Evidence
    2.05
    Evidence
    2.03
     EVIDENCE
    2.00
     PROOF
    1.96
     Proof
    1.95
    proof
    1.91
    Proof
    1.90
    Act Density 1.307%

    No Known Activations