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

    Neuronpedia

    INDEX
    Explanations

    terms related to the importance of various concepts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dea
    -0.15
    führ
    -0.15
    _pemb
    -0.14
    gam
    -0.14
     tay
    -0.13
    dig
    -0.13
    Callbacks
    -0.13
    aspers
    -0.13
    lov
    -0.13
    ango
    -0.13
    POSITIVE LOGITS
     componente
    0.17
     to
    0.16
     component
    0.16
     towards
    0.16
    ikt
    0.15
    yz
    0.15
     Keys
    0.15
    /help
    0.15
     toward
    0.15
    ksi
    0.14
    Act Density 0.063%

    No Known Activations