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

    Neuronpedia

    INDEX
    Explanations

    terms related to depth measurements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Nico
    -0.72
    rowad
    -0.62
    </b>
    -0.61
    $",
    -0.60
    )|^{
    -0.60
     Wey
    -0.58
    Nico
    -0.58
     ISC
    -0.57
    er
    -0.56
    дже
    -0.55
    POSITIVE LOGITS
     unknownFields
    1.09
     DEPTH
    1.08
    دانشنامهٔ
    1.04
    ValueStyle
    0.97
    IVEREF
    0.96
    Depth
    0.90
    urtstag
    0.88
     GenerationType
    0.88
    #+#
    0.87
     Depth
    0.86
    Act Density 0.006%

    No Known Activations