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

    Neuronpedia

    INDEX
    Explanations

    formal statements and definitions related to mathematical proofs and results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    interopRequire
    -0.76
    sizeCache
    -0.75
    =$?
    -0.65
    ?}",
    -0.63
     '\\;'
    -0.63
    ]")]
    -0.62
    StructEnd
    -0.61
    +:+
    -0.60
     himo
    -0.59
    HostException
    -0.59
    POSITIVE LOGITS
     niedersachsen
    0.61
     universale
    0.59
     Monfieur
    0.58
     leſs
    0.57
     dacia
    0.56
     whofe
    0.56
     Efq
    0.56
     uſed
    0.55
     engraved
    0.55
     himſelf
    0.55
    Act Density 0.085%

    No Known Activations