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

    Neuronpedia

    INDEX
    Explanations

    technical or scientific terms related to measurements and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wheel
    -0.18
     Writer
    -0.18
    Writer
    -0.18
     Wrapper
    -0.16
    Wrapper
    -0.16
    Workspace
    -0.16
     Writers
    -0.15
    eway
    -0.15
     Warn
    -0.15
     Wheel
    -0.15
    POSITIVE LOGITS
     w
    1.80
    w
    0.85
    =w
    0.83
    (w
    0.78
    .w
    0.77
    *w
    0.77
    [w
    0.73
    :w
    0.71
    "w
    0.70
    	w
    0.67
    Act Density 0.506%

    No Known Activations