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

    Neuronpedia

    INDEX
    Explanations

    words related to programming syntax and functions

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the article "a" in various contexts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Atkins
    -0.78
    AIDS
    -0.77
     Oprah
    -0.77
    OTUS
    -0.70
    African
    -0.70
    NPR
    -0.69
    oft
    -0.67
    atton
    -0.67
    NP
    -0.65
    ampunk
    -0.65
    POSITIVE LOGITS
     dummy
    1.12
     bunch
    1.05
     placeholder
    0.99
     subset
    0.99
    uras
    0.97
     single
    0.96
     specific
    0.96
     separate
    0.95
     suitable
    0.94
     random
    0.92
    Act Density 0.319%

    No Known Activations