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

    Neuronpedia

    INDEX
    Explanations

    phrases where something is emphasized or highlighted

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "pretty much."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glass
    -0.68
    odium
    -0.67
    raft
    -0.67
    microsoft
    -0.64
    aline
    -0.63
    yd
    -0.63
    may
    -0.63
    len
    -0.63
    rive
    -0.62
    Tweet
    -0.62
    POSITIVE LOGITS
     everywhere
    1.16
     everything
    1.03
     everyone
    1.02
     everybody
    1.00
     EVERY
    0.94
     nonexistent
    0.94
     every
    0.94
     identical
    0.92
     indistinguishable
    0.90
     anything
    0.90
    Act Density 0.075%

    No Known Activations