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

    Neuronpedia

    INDEX
    Explanations

    the word "this" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of empty or null content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¹ãĥĪ
    -0.83
    Ń·
    -0.81
    icons
    -0.78
    oran
    -0.76
    esm
    -0.75
    borg
    -0.72
    ivas
    -0.72
    meric
    -0.71
    alties
    -0.70
     è£ıè¦ļéĨĴ
    -0.70
    POSITIVE LOGITS
     guy
    0.97
     particular
    0.93
     trope
    0.91
     phenomenon
    0.91
     arrangement
    0.91
     newfound
    0.89
     predicament
    0.88
     nifty
    0.86
     discrepancy
    0.85
     arrang
    0.85
    Act Density 0.219%

    No Known Activations