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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or estimation of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bender
    -0.79
     Parables
    -0.76
    iland
    -0.75
    phabet
    -0.73
    ority
    -0.69
    oran
    -0.68
    eria
    -0.67
    itiz
    -0.64
     gulf
    -0.63
    enegger
    -0.62
    POSITIVE LOGITS
     noon
    1.12
     midday
    1.07
     midnight
    0.98
     dusk
    0.97
     dawn
    0.90
     jun
    0.86
     ripe
    0.85
     behest
    0.83
     sunset
    0.82
     speeds
    0.81
    Act Density 0.023%

    No Known Activations