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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "a" followed by a proper noun

    oai_token-act-pair · gpt-3.5-turbo

    articles and nouns that begin with the letter "a"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Versions
    -0.84
    APD
    -0.83
    ['
    -0.82
    daq
    -0.80
    Alien
    -0.79
    EMA
    -0.79
    Aim
    -0.75
    xd
    -0.74
    Īè
    -0.74
    DragonMagazine
    -0.73
    POSITIVE LOGITS
     powerful
    1.02
     versatile
    1.00
     wonderful
    0.99
     unique
    0.98
     fantastic
    0.97
     recurring
    0.96
     fascinating
    0.94
     fictional
    0.94
     terrific
    0.93
     wonderfully
    0.92
    Act Density 0.120%

    No Known Activations