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

    Neuronpedia

    INDEX
    Explanations

    references to rankings and ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucci
    -0.18
    weis
    -0.17
    inic
    -0.17
    zon
    -0.16
    esto
    -0.16
    specialchars
    -0.14
    rors
    -0.14
    ucas
    -0.14
     equivalents
    -0.14
    hips
    -0.14
    POSITIVE LOGITS
    -notch
    0.36
    pling
    0.35
     notch
    0.34
    ographical
    0.31
    ography
    0.28
    -secret
    0.27
    -flight
    0.27
    amax
    0.26
    pled
    0.25
    ical
    0.25
    Act Density 0.029%

    No Known Activations