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

    Neuronpedia

    INDEX
    Explanations

    superlatives, specifically the word "most" followed by an adjective, indicating prominence or extremity

    oai_token-act-pair · gpt-3.5-turbo

    the superlative form of the word "most."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.76
    æ©
    -0.72
     Travels
    -0.65
    rompt
    -0.64
     Films
    -0.64
    instead
    -0.62
    halla
    -0.62
    heid
    -0.62
    ÃĥÃĤ
    -0.61
    amins
    -0.61
    POSITIVE LOGITS
     important
    0.96
     obvious
    0.89
    likely
    0.89
     profitable
    0.88
     interesting
    0.85
     noticeable
    0.84
     notable
    0.84
     likely
    0.83
     importantly
    0.83
     exciting
    0.82
    Act Density 0.069%

    No Known Activations