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

    Neuronpedia

    INDEX
    Explanations

    concepts related to complexity and depth in explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪئ
    -0.14
     @$_
    -0.14
    ÙijÙĩ
    -0.14
    ulumi
    -0.13
     yine
    -0.13
    ^K
    -0.13
    \Common
    -0.13
    fty
    -0.13
     |_|
    -0.12
    кÑĤÑĥ
    -0.12
    POSITIVE LOGITS
     more
    0.85
    more
    0.66
     MORE
    0.60
     More
    0.58
    More
    0.57
     hơn
    0.56
     más
    0.53
     mehr
    0.52
    _more
    0.51
     wiÄĻcej
    0.51
    Act Density 0.171%

    No Known Activations