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

    Neuronpedia

    INDEX
    Explanations

    terms related to minimum requirements or thresholds

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Min
    -0.66
     Max
    -0.65
    Min
    -0.64
    Max
    -0.64
    istive
    -0.64
    min
    -0.63
     min
    -0.62
     Wil
    -0.60
     جدًا
    -0.60
     Perkins
    -0.59
    POSITIVE LOGITS
     Walkover
    0.85
    Rhestr
    0.85
     Saitama
    0.82
    transQ
    0.81
    UpInside
    0.81
    skull
    0.79
    Personensuche
    0.78
     Lombok
    0.78
    0.77
    >>()
    0.77
    Act Density 0.028%

    No Known Activations