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

    Neuronpedia

    INDEX
    Explanations

    quantities or numbers in relation to a specific activity or event

    oai_token-act-pair · gpt-3.5-turbo

    numerical references related to quantities or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actic
    -0.67
    amaru
    -0.62
    achi
    -0.62
    ilic
    -0.61
    iage
    -0.57
    ogi
    -0.56
    idy
    -0.56
    rots
    -0.56
    PAC
    -0.56
    roth
    -0.56
    POSITIVE LOGITS
     mornings
    0.90
    uously
    0.85
     weeks
    0.83
     months
    0.82
    aciously
    0.80
     Nights
    0.77
     nights
    0.76
     days
    0.76
     times
    0.74
    teenth
    0.71
    Act Density 0.164%

    No Known Activations