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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or questioning in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoField
    -0.37
    Биография
    -0.35
    SaveVideo
    -0.34
    ⎨
    -0.34
    为例
    -0.34
    collana
    -0.33
    assertj
    -0.32
    netbeans
    -0.32
    selaer
    -0.31
    ようになった
    -0.31
    POSITIVE LOGITS
     something
    4.53
    something
    3.91
    Something
    3.83
     Something
    3.77
     SOMETHING
    3.13
     qualcosa
    3.08
     somethin
    2.80
     sesuatu
    2.77
     iets
    2.64
     coś
    2.59
    Act Density 1.286%

    No Known Activations