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

    Neuronpedia

    INDEX
    Explanations

    references to personal safety and security incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñīина
    -0.16
    ики
    -0.15
    ifie
    -0.15
    üre
    -0.15
    haven
    -0.15
    rid
    -0.15
     xÆ°Æ¡ng
    -0.14
    oba
    -0.14
    ãĥ¼ãĥĬ
    -0.14
    Fixture
    -0.14
    POSITIVE LOGITS
    (New
    0.20
    by
    0.19
     by
    0.17
     Sesso
    0.15
     Tear
    0.15
     Hindered
    0.14
     Blake
    0.14
     twin
    0.14
     serial
    0.14
     Keller
    0.13
    Act Density 0.060%

    No Known Activations