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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with configuration parameters in a technical or programming context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Theory
    -0.53
    Theory
    -0.53
     Bark
    -0.51
    mak
    -0.50
     Ank
    -0.48
     Ne
    -0.47
     typelib
    -0.47
     Cec
    -0.47
     /\.
    -0.47
     theory
    -0.47
    POSITIVE LOGITS
     Debussy
    0.69
    الدراسه
    0.66
     stanzas
    0.66
    UnknownFields
    0.65
    Mustard
    0.65
    fordshire
    0.65
     Allahabad
    0.65
    rsiniz
    0.64
     Wikisource
    0.64
    insegna
    0.64
    Act Density 0.042%

    No Known Activations