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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to scientific papers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    цездатний
    -0.94
     gradova
    -0.68
    ⓧ
    -0.65
    EndGlobalSection
    -0.65
     EnglishChoose
    -0.62
    BeginContext
    -0.61
    पया
    -0.60
    ArgsConstructor
    -0.60
     الحره
    -0.59
     pinulongan
    -0.57
    POSITIVE LOGITS
     {}'.
    0.62
     {}".
    0.57
    rungsseite
    0.55
    nastics
    0.52
    agua
    0.50
    grounds
    0.49
     pii
    0.49
    sociation
    0.48
    freiheit
    0.48
    UnusedPrivate
    0.48
    Act Density 0.020%

    No Known Activations