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

    Neuronpedia

    INDEX
    Explanations

    phrases related to poor quality or negative conditions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.65
    s
    -0.65
    uVar
    -0.63
     Ayuda
    -0.61
    Salle
    -0.59
    ьаж
    -0.59
    blich
    -0.58
    ally
    -0.57
     Landau
    -0.57
     پرس
    -0.56
    POSITIVE LOGITS
    Datuak
    0.91
     POOR
    0.86
     Poor
    0.85
    UpInside
    0.82
    poor
    0.81
     Poon
    0.81
     Mier
    0.80
    Laure
    0.78
    PerformLayout
    0.77
    BagConstraints
    0.76
    Act Density 0.008%

    No Known Activations