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

    Neuronpedia

    INDEX
    Explanations

    words related to counting and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     userEmail
    -0.62
     ApiService
    -0.61
     bestem
    -0.61
     Pexels
    -0.60
     Schal
    -0.60
     Chalmers
    -0.59
     Etapa
    -0.59
     pekan
    -0.59
     apt
    -0.58
    Geplaatst
    -0.57
    POSITIVE LOGITS
     counts
    1.36
     COUNT
    1.33
     counted
    1.30
     count
    1.30
    counts
    1.29
    count
    1.25
     Count
    1.25
    COUNT
    1.20
     Counts
    1.18
     Counting
    1.17
    Act Density 0.083%

    No Known Activations