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

    Neuronpedia

    INDEX
    Explanations

    expressions related to capability and existential reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bul
    -0.14
    &m
    -0.14
     pitch
    -0.14
     Stranger
    -0.13
    uu
    -0.13
     Theresa
    -0.13
     cre
    -0.13
     sn
    -0.13
    âŁ
    -0.13
    vrier
    -0.13
    POSITIVE LOGITS
    ombs
    0.15
    /Runtime
    0.15
    eland
    0.14
     ÑĪп
    0.14
    ยà¸ĩ
    0.14
    ÏĥÏĦαν
    0.14
    KANJI
    0.14
    еÑĢÑĮ
    0.14
    lands
    0.13
    адки
    0.13
    Act Density 0.001%

    No Known Activations