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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "public" and its variations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¶
    -0.20
    isson
    -0.16
     Grass
    -0.16
    /lg
    -0.15
    flate
    -0.15
     Nat
    -0.14
     Ded
    -0.14
    icit
    -0.14
    azio
    -0.14
    ernity
    -0.14
    POSITIVE LOGITS
    arters
    0.17
     "-//
    0.16
    uben
    0.15
    arts
    0.15
    suite
    0.15
    iverz
    0.14
    ırı
    0.14
    еÑĦ
    0.14
     shave
    0.13
    handle
    0.13
    Act Density 0.003%

    No Known Activations