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

    Neuronpedia

    INDEX
    Explanations

    decimal points in numerical values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     vertes
    -0.62
    laceae
    -0.62
     roche
    -0.61
     capilar
    -0.59
     veo
    -0.59
    jeuner
    -0.58
     foncé
    -0.57
     revanche
    -0.57
     linguistique
    -0.57
     Clarissa
    -0.57
    POSITIVE LOGITS
     utafitiHapana
    0.67
    ArgsConstructor
    0.60
     BufferedWriter
    0.60
    ($__
    0.60
    setLayoutManager
    0.59
     ctypes
    0.58
    twimg
    0.57
    i
    0.57
    iyor
    0.56
    AxisAlignment
    0.55
    Act Density 0.070%

    No Known Activations