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

    Neuronpedia

    INDEX
    Explanations

    keywords related to specific individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bjerg
    -0.17
    etro
    -0.15
    vard
    -0.15
    utsche
    -0.15
    883
    -0.14
    URRENCY
    -0.14
    çĤī
    -0.14
    adic
    -0.14
    Forward
    -0.13
    lop
    -0.13
    POSITIVE LOGITS
    945
    0.16
    ynn
    0.15
    akedown
    0.15
    anger
    0.14
    apiro
    0.14
    Wilson
    0.14
     Falk
    0.14
    ãĥ¯ãĤ¤ãĥĪ
    0.14
     Wilson
    0.14
    ourg
    0.14
    Act Density 0.019%

    No Known Activations