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

    Neuronpedia

    INDEX
    Explanations

    hyphenated phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to hands-on experiences or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pens
    -0.60
     Jacket
    -0.59
     pulp
    -0.59
     coat
    -0.59
     frig
    -0.58
     Coat
    -0.58
     gloom
    -0.58
     Defendants
    -0.57
     Ala
    -0.57
     Cruiser
    -0.57
    POSITIVE LOGITS
    everal
    1.14
    ettings
    1.10
    hift
    1.07
    peed
    1.05
    sembly
    1.03
    uper
    0.99
    ource
    0.99
    hell
    0.96
    olutions
    0.96
    sein
    0.94
    Act Density 0.058%

    No Known Activations