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

    Neuronpedia

    INDEX
    Explanations

    items or entities listed in a ranking or list format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ended
    -0.73
    aeus
    -0.71
    gery
    -0.69
    ousy
    -0.68
    entimes
    -0.66
    nces
    -0.65
    nce
    -0.63
    ideon
    -0.63
    matter
    -0.61
    amiya
    -0.60
    POSITIVE LOGITS
     list
    1.58
     lists
    1.32
     checklist
    1.16
     radar
    1.13
    LIST
    1.13
     blacklist
    1.11
    list
    1.06
     charts
    1.03
     Lists
    1.03
     List
    0.99
    Act Density 0.162%

    No Known Activations