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

    Neuronpedia

    INDEX
    Explanations

    words that indicate capability or suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.28
    ing
    -0.26
    edb
    -0.22
    arily
    -0.22
    ical
    -0.20
    emann
    -0.17
    naires
    -0.17
    fulness
    -0.17
    ese
    -0.17
    naire
    -0.17
    POSITIVE LOGITS
    able
    0.25
    atable
    0.25
     enough
    0.23
    /print
    0.23
    ble
    0.20
    /un
    0.20
    mente
    0.20
    ABLE
    0.20
    /non
    0.20
    /read
    0.19
    Act Density 0.151%

    No Known Activations