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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kers
    -0.16
    bers
    -0.15
    ongan
    -0.14
    PAT
    -0.14
    achi
    -0.14
    leting
    -0.14
    ulton
    -0.14
    oris
    -0.13
    gere
    -0.13
    ì¹ĺëĬĶ
    -0.13
    POSITIVE LOGITS
    mith
    0.17
     steps
    0.17
     instruction
    0.16
    اÙĦع
    0.16
    instruction
    0.16
     průbÄĽhu
    0.16
    oppable
    0.15
     instructions
    0.15
    instructions
    0.15
    ueue
    0.15
    Act Density 0.034%

    No Known Activations