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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omik
    -0.16
     VARIABLE
    -0.14
    modity
    -0.13
    aits
    -0.13
    oret
    -0.13
    cot
    -0.13
    culated
    -0.13
    alon
    -0.13
    uron
    -0.13
    faq
    -0.12
    POSITIVE LOGITS
     activity
    0.29
     talk
    0.27
     discussion
    0.26
     attention
    0.26
     emphasis
    0.24
     debate
    0.24
    activity
    0.23
     ink
    0.22
     effort
    0.22
     hoop
    0.22
    Act Density 0.125%

    No Known Activations