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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions indicating arrival or emergence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лик
    -0.14
    quette
    -0.14
    rát
    -0.14
    Ĺı
    -0.14
    ummings
    -0.14
    las
    -0.14
    ogram
    -0.14
    eros
    -0.14
    bart
    -0.13
    ãĥ¼ãĥĹ
    -0.13
    POSITIVE LOGITS
    ëıĮ
    0.14
    uder
    0.14
    ixin
    0.14
    akan
    0.13
     iron
    0.13
    TES
    0.13
    mw
    0.13
    CACHE
    0.13
    tell
    0.13
     Transition
    0.13
    Act Density 0.016%

    No Known Activations