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

    Neuronpedia

    INDEX
    Explanations

    references to people, particularly those involved in various roles and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¹ĭä¸Ģ
    -0.15
    oder
    -0.14
    áce
    -0.13
    unts
    -0.13
    ügen
    -0.13
    Ïģη
    -0.13
    clud
    -0.13
    ager
    -0.13
    embros
    -0.13
    gether
    -0.13
    POSITIVE LOGITS
     with
    0.23
     who
    0.22
     without
    0.19
     everywhere
    0.19
    with
    0.18
     whose
    0.18
     nÃło
    0.17
    -first
    0.16
    without
    0.16
    who
    0.16
    Act Density 0.310%

    No Known Activations