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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate sequence or hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zia
    -0.23
    ulse
    -0.15
    YST
    -0.15
    ÄIJT
    -0.14
    uft
    -0.14
     newInstance
    -0.14
    angan
    -0.14
    彩
    -0.14
    åIJįçĦ¡ãģĹãģķãĤĵ
    -0.13
    unami
    -0.13
    POSITIVE LOGITS
    .persistent
    0.16
    ipc
    0.14
    ython
    0.14
    kop
    0.14
    oned
    0.14
     oku
    0.14
    esser
    0.14
    orpor
    0.13
    sted
    0.13
    quier
    0.13
    Act Density 0.026%

    No Known Activations