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

    Neuronpedia

    INDEX
    Explanations

    questions and queries related to understanding and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -cigaret
    -0.15
     Kab
    -0.15
    antu
    -0.15
    ÑĢоб
    -0.14
    bsp
    -0.14
    ÑĥлÑĮ
    -0.14
    amespace
    -0.14
    oeff
    -0.13
    oux
    -0.13
    [action
    -0.13
    POSITIVE LOGITS
    adc
    0.15
    heimer
    0.14
    ibble
    0.14
    ounder
    0.14
    elan
    0.13
    adia
    0.13
    Sale
    0.13
    æĬ±
    0.13
    enza
    0.13
    enberg
    0.13
    Act Density 0.036%

    No Known Activations