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
    anship
    -0.92
    QL
    -0.84
    neg
    -0.83
    onym
    -0.83
    Ô
    -0.82
    akings
    -0.82
    ealous
    -0.79
    adier
    -0.78
    NR
    -0.78
    Yesterday
    -0.77
    POSITIVE LOGITS
     rectangular
    1.14
     oval
    1.11
     humanoid
    1.11
     spherical
    1.06
     spheres
    1.05
     cardboard
    1.04
     plastic
    1.03
     objects
    1.02
     cyl
    1.02
     holes
    0.99
    Act Density 0.150%

    No Known Activations