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

    Neuronpedia

    INDEX
    Explanations

    the letter "a" followed by a digit

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Atkins
    -0.71
     indign
    -0.70
     EVs
    -0.67
     sorts
    -0.65
     HMS
    -0.65
     infield
    -0.64
     ATK
    -0.63
     outfield
    -0.62
     Oscar
    -0.60
     eventual
    -0.60
    POSITIVE LOGITS
    ctors
    1.06
    vertisement
    1.05
    ria
    1.03
    uras
    1.03
    merce
    1.02
    sembly
    1.01
    lder
    0.99
    ctions
    0.99
    eon
    0.97
    rouse
    0.96
    Act Density 0.234%

    No Known Activations