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

    Neuronpedia

    INDEX
    Explanations

    uncommon or unusual words

    oai_token-act-pair · gpt-3.5-turbo

    terms related to unreleased content or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.75
     Bind
    -0.69
     Bernstein
    -0.68
     Elephant
    -0.68
     GOODMAN
    -0.67
     Shades
    -0.67
     Devils
    -0.65
    uyomi
    -0.65
    ospace
    -0.63
     Mayhem
    -0.62
    POSITIVE LOGITS
    leased
    1.13
    achable
    1.12
    ason
    0.96
    agan
    0.95
    peat
    0.90
    ached
    0.88
    edy
    0.87
    classified
    0.84
    ceptive
    0.83
    tted
    0.82
    Act Density 0.020%

    No Known Activations