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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or doubt expressed in a conversational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.69
    IsPostBack
    -0.57
    drawSprites
    -0.54
    олові
    -0.52
    sianic
    -0.52
     Arhivirano
    -0.52
    ywna
    -0.50
    Parcelize
    -0.50
    resso
    -0.49
     @}
    -0.49
    POSITIVE LOGITS
     something
    4.08
    something
    3.52
    Something
    3.31
     Something
    3.23
     SOMETHING
    2.75
     qualcosa
    2.52
     quelque
    2.49
     somethin
    2.46
     algo
    2.19
     något
    2.09
    Act Density 0.498%

    No Known Activations