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

    Neuronpedia

    INDEX
    Explanations

    descriptions of shapes and structures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     drap
    -0.77
     klu
    -0.74
     notor
    -0.73
     espé
    -0.72
     stoff
    -0.72
     incess
    -0.71
     sogget
    -0.71
     cabrio
    -0.71
     Sitten
    -0.70
     robus
    -0.69
    POSITIVE LOGITS
     shaped
    0.97
     shape
    0.89
    shaped
    0.85
     shapes
    0.73
    shape
    0.72
    haped
    0.64
    Shaped
    0.63
     pattern
    0.61
     Shaped
    0.58
    Shape
    0.58
    Act Density 0.279%

    No Known Activations