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

    Neuronpedia

    INDEX
    Explanations

    code comments or documentation indicators

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    #
    -0.91
     GenerationType
    -0.88
     snoring
    -0.75
     &___
    -0.69
    ViewFeatures
    -0.68
     Савезне
    -0.68
     auroit
    -0.64
     étoit
    -0.63
    oredCriteria
    -0.63
    PYX
    -0.62
    POSITIVE LOGITS
    antaranya
    0.62
    >|</
    0.61
     connexes
    0.59
    Източници
    0.58
    lengths
    0.57
     Winn
    0.57
    ILayout
    0.56
     Nen
    0.56
     Koll
    0.54
     Vij
    0.53
    Act Density 0.005%

    No Known Activations