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

    Neuronpedia

    INDEX
    Explanations

    words related to quantity or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical references to counts or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rum
    -0.72
    activity
    -0.65
    efficiency
    -0.64
    luck
    -0.62
    eston
    -0.61
    rology
    -0.60
    nce
    -0.59
     Fol
    -0.58
     Activities
    -0.58
    rium
    -0.57
    POSITIVE LOGITS
     apiece
    1.69
     totaling
    1.23
    poons
    1.18
     consecut
    1.05
    paces
    1.00
     per
    0.95
    hips
    0.93
     respectively
    0.91
     simultaneously
    0.84
    dozen
    0.81
    Act Density 0.274%

    No Known Activations