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

    Neuronpedia

    INDEX
    Explanations

    shapes or forms

    oai_token-act-pair · gpt-3.5-turbo

    references to various shapes and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onte
    -0.73
     Mub
    -0.72
    aires
    -0.69
    ammy
    -0.67
    govtrack
    -0.66
    iance
    -0.64
    cffffcc
    -0.62
    endment
    -0.62
    UES
    -0.61
    unts
    -0.60
    POSITIVE LOGITS
     shif
    1.02
    forms
    0.97
    ly
    0.94
     shape
    0.91
    shape
    0.91
    forming
    0.88
    Shape
    0.86
    changing
    0.83
    liness
    0.82
    form
    0.82
    Act Density 0.067%

    No Known Activations