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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing emotions or personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    êu
    -0.14
    umont
    -0.14
    makt
    -0.13
    anke
    -0.13
    patch
    -0.13
    1
    -0.13
     baggage
    -0.13
    tak
    -0.13
    ubre
    -0.13
    ÅĤy
    -0.13
    POSITIVE LOGITS
     ï¿¥
    0.18
    illet
    0.17
    istar
    0.15
    .ribbon
    0.15
     fetisch
    0.15
    اÛĮت
    0.14
    /lic
    0.14
    Ïģια
    0.14
    IBUTES
    0.14
    ICAST
    0.14
    Act Density 0.104%

    No Known Activations