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

    Neuronpedia

    INDEX
    Explanations

    comparative expressions related to quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating quantities or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elf
    -0.64
    ID
    -0.63
    fen
    -0.63
    Enc
    -0.62
    ACY
    -0.61
    bara
    -0.60
    ICS
    -0.59
    Auth
    -0.59
    STAR
    -0.59
    ISM
    -0.59
    POSITIVE LOGITS
     than
    1.15
    than
    0.94
     Than
    0.81
     paced
    0.78
     statistically
    0.74
     (~
    0.73
     (>
    0.73
     overall
    0.73
     economically
    0.73
     (+
    0.71
    Act Density 0.192%

    No Known Activations