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

    Neuronpedia

    INDEX
    Explanations

    tech-related terms and instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to notable posts and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plurality
    -0.75
     Flavoring
    -0.70
    opped
    -0.70
    zinski
    -0.69
     perceived
    -0.69
     sudden
    -0.66
     indiscrim
    -0.65
    Ħ¢
    -0.65
    acists
    -0.64
    intention
    -0.64
    POSITIVE LOGITS
     pdf
    1.25
     http
    1.07
    pdf
    1.07
     LINK
    1.06
     Github
    1.03
    PDF
    1.01
    http
    1.01
     https
    1.01
     www
    1.00
    https
    1.00
    Act Density 0.651%

    No Known Activations