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

    Neuronpedia

    INDEX
    Explanations

    verbs or noun phrases related to software programming and functions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    AIDS
    -0.89
    âĢİ
    -0.78
    Hon
    -0.75
    America
    -0.75
     Oprah
    -0.74
    African
    -0.70
    Gov
    -0.70
     abortions
    -0.69
    ESPN
    -0.69
    LGBT
    -0.68
    POSITIVE LOGITS
     lot
    1.13
     bunch
    1.05
     single
    1.05
     finite
    1.03
    uras
    1.02
     suitable
    1.00
     variety
    0.98
     subset
    0.98
     continuous
    0.97
     combination
    0.97
    Act Density 0.493%

    No Known Activations