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

    Neuronpedia

    INDEX
    Explanations

    references to high-quality visual content or collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Insensitive
    -0.17
     DISCLAIMS
    -0.16
    oten
    -0.15
    á»ijng
    -0.15
    okit
    -0.15
    ÑģиÑħ
    -0.15
    ibold
    -0.15
    /swagger
    -0.15
    jee
    -0.14
    ìĤ´
    -0.14
    POSITIVE LOGITS
     mixed
    0.19
     believed
    0.15
     among
    0.15
     Mixed
    0.15
    783
    0.15
     Crane
    0.14
     Cheese
    0.14
    disp
    0.14
     choices
    0.14
    mixed
    0.14
    Act Density 0.032%

    No Known Activations