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

    Neuronpedia

    INDEX
    Explanations

    superlative expressions and the word "as" indicating comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansom
    -0.16
    icros
    -0.16
    erdale
    -0.15
    tlement
    -0.15
    -placeholder
    -0.15
    semblies
    -0.15
    sthrough
    -0.14
    tractive
    -0.14
    uzu
    -0.14
    processable
    -0.14
    POSITIVE LOGITS
    ually
    0.25
    fully
    0.23
    arily
    0.23
    ally
    0.23
    ients
    0.23
    entially
    0.23
    ently
    0.22
    antly
    0.22
    ically
    0.21
    lessly
    0.21
    Act Density 0.237%

    No Known Activations