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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -1.40
    ever
    -1.23
    ised
    -1.16
    ities
    -1.14
    ized
    -1.13
    ists
    -1.08
    ist
    -1.06
    ette
    -1.04
    ef
    -0.99
    ize
    -0.98
    POSITIVE LOGITS
    ations
    0.56
    ors
    0.53
    ory
    0.52
    aneous
    0.50
    ational
    0.50
    orial
    0.49
    arian
    0.48
    ation
    0.47
    ative
    0.45
    arians
    0.45
    Act Density 7.243%

    No Known Activations