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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or symbols, particularly in the context of matrices or equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.68
     snippetHide
    -0.62
    scalatest
    -0.62
    furl
    -0.61
    TagMode
    -0.61
    Rujukan
    -0.59
    verständlich
    -0.59
    ünkü
    -0.59
    migrationBuilder
    -0.58
     impati
    -0.57
    POSITIVE LOGITS
    </strong>
    0.71
     transfieras
    0.66
    enterOuterAlt
    0.63
    </code>
    0.61
    unchecked
    0.59
    exitRule
    0.59
    #+#
    0.56
     backing
    0.56
     mengen
    0.56
     kapture
    0.55
    Act Density 0.017%

    No Known Activations