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

    Neuronpedia

    INDEX
    Explanations

    phrases related to capability or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ness
    -0.20
    emente
    -0.19
    NESS
    -0.17
    rina
    -0.16
    acs
    -0.15
    iness
    -0.15
    enate
    -0.15
    baugh
    -0.15
    liness
    -0.15
    ocks
    -0.15
    POSITIVE LOGITS
     to
    0.25
    uable
    0.19
    ted
    0.19
     able
    0.18
    åĪ°çļĦ
    0.18
    ble
    0.18
    pped
    0.17
     Able
    0.17
    bled
    0.17
    azed
    0.16
    Act Density 0.051%

    No Known Activations