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

    Neuronpedia

    INDEX
    Explanations

    words related to physical barriers or thickness, especially in the context of materials or layers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.64
    évaluateur
    -0.60
     resourceCulture
    -0.59
    AutoScale
    -0.58
    clairage
    -0.54
     Roskov
    -0.54
     Steuern
    -0.54
     steamboat
    -0.53
     ergon
    -0.53
     Приступљено
    -0.52
    POSITIVE LOGITS
     thickness
    0.97
    thickness
    0.83
     thicknesses
    0.81
     thicker
    0.80
     thick
    0.77
    Thickness
    0.77
     layer
    0.77
     Thickness
    0.74
     layers
    0.73
     thin
    0.69
    Act Density 0.409%

    No Known Activations