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

    Neuronpedia

    INDEX
    Explanations

    language related to the handling and disclosure of personal information and legal compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    slick
    -0.16
    avar
    -0.15
     Ama
    -0.15
    urdu
    -0.15
    erea
    -0.14
    remain
    -0.14
     éĥ
    -0.14
    ìĿ¸íĬ¸
    -0.14
    ÑĥÑĢÑĭ
    -0.14
    irectional
    -0.14
    POSITIVE LOGITS
     nackte
    0.18
    çĽ¸ä¿¡
    0.16
    odel
    0.16
    iode
    0.15
    ugen
    0.14
     believes
    0.14
     imm
    0.14
    ossa
    0.14
    046
    0.14
    aud
    0.14
    Act Density 0.019%

    No Known Activations