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

    Neuronpedia

    INDEX
    Explanations

    expressions of concern and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.15
    ÑĥÑĢи
    -0.15
    ertz
    -0.15
    umbn
    -0.15
    agne
    -0.14
    ини
    -0.14
    emez
    -0.14
    ande
    -0.14
     pled
    -0.14
    élé
    -0.13
    POSITIVE LOGITS
     themselves
    0.17
    han
    0.15
    ê¸Ī
    0.15
    çĶļèĩ³
    0.14
    823
    0.14
     Conc
    0.14
    ENS
    0.14
    odi
    0.14
    ieber
    0.13
    sburg
    0.13
    Act Density 0.277%

    No Known Activations