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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty and clarification in discussions or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.65
    +#+#
    -0.62
    UrlResolution
    -0.59
     مشين
    -0.58
    WebServlet
    -0.58
    født
    -0.57
    érience
    -0.56
     فريبيس
    -0.56
    fromCharCode
    -0.54
     NavController
    -0.53
    POSITIVE LOGITS
     exact
    3.30
    exact
    2.89
     exactly
    2.84
     Exact
    2.68
    exactly
    2.60
    Exact
    2.58
     exacte
    2.57
     precise
    2.54
    precise
    2.52
     Exactly
    2.46
    Act Density 0.710%

    No Known Activations