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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causal relationships or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     as
    -0.16
    adden
    -0.16
     als
    -0.15
    ä½ľä¸º
    -0.15
    hed
    -0.14
    vre
    -0.14
    اÙĤ
    -0.14
    ington
    -0.14
    il
    -0.14
    ising
    -0.14
    POSITIVE LOGITS
     of
    0.28
    antly
    0.22
     thereof
    0.21
     Ñĩого
    0.18
     Ñĩего
    0.18
     của
    0.18
    pNet
    0.17
     consequence
    0.17
    avra
    0.16
    ardy
    0.16
    Act Density 0.021%

    No Known Activations