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

    Neuronpedia

    INDEX
    Explanations

    references to introverted characteristics or personas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exp
    -0.15
    urf
    -0.15
    ãģĤãĤĬãģ¾ãģĽãĤĵ
    -0.14
     Hüs
    -0.14
    duk
    -0.14
    earch
    -0.14
    aturas
    -0.14
    UnityEngine
    -0.14
     equ
    -0.14
    esub
    -0.14
    POSITIVE LOGITS
    å¾
    0.19
     Ñĥгл
    0.18
    SizePolicy
    0.15
    견
    0.15
    Trou
    0.14
    dy
    0.14
    اÙĨا
    0.14
    tracted
    0.14
    .GetKey
    0.14
    Wrap
    0.14
    Act Density 0.004%

    No Known Activations