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

    Neuronpedia

    INDEX
    Explanations

    words with the prefix "pl" or words that contain "pl"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aml
    -0.16
    conj
    -0.15
    invite
    -0.15
    ABI
    -0.14
    icted
    -0.14
    jekt
    -0.14
    sei
    -0.14
    kul
    -0.13
    apiro
    -0.13
    udas
    -0.13
    POSITIVE LOGITS
    anned
    0.25
    ugs
    0.24
    ural
    0.24
    enty
    0.23
    ough
    0.23
    anning
    0.23
    ucky
    0.22
    ugging
    0.22
    ugged
    0.22
    umb
    0.22
    Act Density 0.011%

    No Known Activations