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

    Neuronpedia

    INDEX
    Explanations

    references to specific programming syntax keywords and constructs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ILLE
    -1.19
    romeda
    -1.14
    pload
    -1.07
    äºĶ
    -1.05
    outube
    -1.01
    nesday
    -1.01
    Leaks
    -0.97
     gul
    -0.96
    vous
    -0.95
    vernment
    -0.92
    POSITIVE LOGITS
    faces
    1.94
    face
    1.86
    ahead
    1.42
    casting
    1.40
    etter
    1.35
    etting
    1.32
    alias
    1.32
    inker
    1.19
    classes
    1.17
    cast
    1.08
    Act Density 0.556%

    No Known Activations