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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong positive emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    *)_
    -0.16
    lements
    -0.14
    ={({
    -0.14
    ázd
    -0.14
    avery
    -0.14
    senal
    -0.14
     اÙĦØ£Ùħر
    -0.14
    aturdays
    -0.13
    ضÙħ
    -0.13
    év
    -0.13
    POSITIVE LOGITS
    iska
    0.17
    den
    0.16
    سÙĥ
    0.14
    jan
    0.14
    jed
    0.14
    यन
    0.14
    orts
    0.13
    ç´
    0.13
    ियन
    0.13
    ={!
    0.13
    Act Density 0.527%

    No Known Activations