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

    Neuronpedia

    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web links in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abruptly
    -0.81
     incorrectly
    -0.77
     accordingly
    -0.76
     appropriately
    -0.74
     incidentally
    -0.74
     overshadow
    -0.74
     Moody
    -0.71
     assigned
    -0.71
     errone
    -0.71
     awaited
    -0.71
    POSITIVE LOGITS
    www
    2.22
    youtu
    1.82
    goo
    1.74
    imgur
    1.65
    forum
    1.63
    tiny
    1.62
    forums
    1.58
    past
    1.56
    blogs
    1.55
    cdn
    1.53
    Act Density 0.019%

    No Known Activations