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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate sources of learning or gaining knowledge through experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ChangeEvent
    -0.14
    .plist
    -0.14
     Glad
    -0.13
    .DEFINE
    -0.13
    yi
    -0.13
    _AI
    -0.13
    å·Ŀ
    -0.13
     uncert
    -0.13
    å±ķ
    -0.13
    ãĤ¥
    -0.13
    POSITIVE LOGITS
    姫
    0.15
    hood
    0.15
    ussy
    0.15
     hood
    0.14
    ño
    0.14
    ilibrium
    0.14
    ruba
    0.14
    /std
    0.14
     cond
    0.13
    hud
    0.13
    Act Density 0.026%

    No Known Activations