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

    Neuronpedia

    INDEX
    Explanations

    frequent top-level categories or classifications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.93
    addGap
    -0.90
    +#+#
    -0.77
    WithFormat
    -0.73
     tartalomajánló
    -0.70
    ImageContext
    -0.67
    nack
    -0.65
    lossians
    -0.64
    ViewFeatures
    -0.63
    InSection
    -0.62
    POSITIVE LOGITS
     Neuk
    0.65
     drawer
    0.63
     pengend
    0.59
    drawer
    0.56
     Drawer
    0.55
     drawers
    0.53
    ußt
    0.53
     propOrder
    0.53
    лосипе
    0.52
     Saras
    0.52
    Act Density 0.016%

    No Known Activations