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

    Neuronpedia

    INDEX
    Explanations

    words related to the surface of objects or locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    \\\\\\\\
    -0.66
    cens
    -0.66
    ards
    -0.65
    mad
    -0.64
     Dek
    -0.64
    beck
    -0.64
    crazy
    -0.63
    dad
    -0.62
    edy
    -0.62
    acha
    -0.62
    POSITIVE LOGITS
     surface
    3.86
     surfaces
    2.69
    surface
    2.62
     Surface
    2.02
     exterior
    1.30
     resur
    1.26
     substrate
    1.12
     surfaced
    1.12
     radar
    1.11
     underside
    1.11
    Act Density 0.022%

    No Known Activations