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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating actions or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ£Ĵ
    -0.17
     Slots
    -0.16
     Thor
    -0.15
    θη
    -0.14
     partitions
    -0.14
     slot
    -0.14
    ãĥ¼ãĥĨãĤ£
    -0.14
     å
    -0.14
     removeAll
    -0.14
     ne
    -0.13
    POSITIVE LOGITS
    enia
    0.16
     Glory
    0.15
     ÎŃν
    0.14
     ÃĿ
    0.14
    iping
    0.14
    bsd
    0.14
    олом
    0.14
    кав
    0.14
    anmar
    0.13
    ì§
    0.13
    Act Density 0.001%

    No Known Activations