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

    Neuronpedia

    INDEX
    Explanations

    words that are commonly used or found

    oai_token-act-pair · gpt-3.5-turbo

    the word "commonly" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongyang
    -0.73
    ilion
    -0.71
     Fury
    -0.70
     Ole
    -0.68
     Equality
    -0.67
    jri
    -0.66
    utenberg
    -0.66
    anth
    -0.65
    anmar
    -0.65
    gur
    -0.64
    POSITIVE LOGITS
     abbrevi
    1.07
     referred
    1.03
    entimes
    1.02
     categorized
    0.95
     seen
    0.90
     encountered
    0.90
     regarded
    0.87
    ensical
    0.86
     known
    0.85
     mistaken
    0.85
    Act Density 0.026%

    No Known Activations