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

    Neuronpedia

    INDEX
    Explanations

    words relating to numerical counts and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivore
    -0.59
    phem
    -0.58
     createState
    -0.55
    Mixture
    -0.52
     αντί
    -0.51
     Administrativna
    -0.51
     Falla
    -0.49
     tây
    -0.48
    ærk
    -0.48
    aringan
    -0.48
    POSITIVE LOGITS
     Count
    1.20
     counting
    1.09
     COUNT
    1.07
     count
    1.07
    Count
    1.05
    COUNT
    1.04
     Counting
    1.01
    counting
    0.98
    count
    0.94
    Counting
    0.92
    Act Density 0.185%

    No Known Activations