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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inh
    -0.14
    ober
    -0.14
    yz
    -0.14
    aná
    -0.13
    à¹ĩà¸Ńà¸ģ
    -0.13
    eness
    -0.13
     esk
    -0.13
    otal
    -0.13
    Marker
    -0.13
     cunning
    -0.12
    POSITIVE LOGITS
    ayo
    0.17
    ÙĪز
    0.14
     Dickinson
    0.14
    ãĢħ
    0.13
    iger
    0.13
    fy
    0.13
    aya
    0.13
    ico
    0.13
    mate
    0.13
    uali
    0.13
    Act Density 0.003%

    No Known Activations