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

    Neuronpedia

    INDEX
    Explanations

    proper names or entities, potentially related to politics or culture

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Est" and its varying forms, indicating a focus on estimates or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FACE
    -0.84
    stocks
    -0.83
     Abyssal
    -0.70
    veyard
    -0.68
    stals
    -0.67
    UGH
    -0.67
    zee
    -0.67
    strap
    -0.67
    birds
    -0.66
    drm
    -0.65
    POSITIVE LOGITS
    ablish
    1.46
    ablished
    1.43
    imate
    1.30
    imates
    1.15
    imating
    1.11
    ablishment
    1.07
    uary
    1.05
    imation
    0.99
    hetically
    0.99
    imated
    0.97
    Act Density 0.015%

    No Known Activations