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

    Neuronpedia

    INDEX
    Explanations

    questions and uncertainty related to actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kah
    -0.17
    gien
    -0.14
    uhan
    -0.14
     Wonder
    -0.13
    UNET
    -0.13
    alu
    -0.13
    emens
    -0.13
     Daly
    -0.13
    £i
    -0.13
    apore
    -0.12
    POSITIVE LOGITS
    oser
    0.19
    zia
    0.16
    egen
    0.15
    heck
    0.15
    оÑī
    0.15
    ourke
    0.15
    ombine
    0.14
    elif
    0.14
    inic
    0.13
     اÙħÛĮر
    0.13
    Act Density 0.097%

    No Known Activations