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

    Neuronpedia

    INDEX
    Explanations

    URLs within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to web URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     increment
    -0.69
     abruptly
    -0.67
     shifts
    -0.65
     firing
    -0.65
     shuff
    -0.63
     assigned
    -0.62
     —
    -0.61
     plate
    -0.61
     shifting
    -0.61
     Plate
    -0.61
    POSITIVE LOGITS
    www
    3.72
     www
    2.19
    http
    1.90
    youtu
    1.61
    ww
    1.52
    https
    1.46
    twitter
    1.31
    goo
    1.27
    wordpress
    1.21
    facebook
    1.21
    Act Density 0.021%

    No Known Activations