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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "back."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aten
    -0.15
    Ø¡
    -0.15
    woke
    -0.15
     Eve
    -0.15
    ÑģÑı
    -0.15
    BACK
    -0.14
     Back
    -0.14
    Back
    -0.14
    ottle
    -0.14
    noÅĽÄĩ
    -0.14
    POSITIVE LOGITS
    antha
    0.16
    InstanceState
    0.16
     eskort
    0.15
     allo
    0.15
     ÑĤодÑĸ
    0.14
    SocketAddress
    0.14
    dma
    0.14
    ocol
    0.14
    landa
    0.14
    enus
    0.14
    Act Density 0.012%

    No Known Activations