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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty, vagueness, or a range of undefined concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VideoCapture
    -0.63
     Mayfield
    -0.53
     Kays
    -0.53
    LabelTagHelper
    -0.52
     vastaan
    -0.52
    brities
    -0.51
     eleventh
    -0.50
    hints
    -0.49
    ]-->
    -0.49
    RTGC
    -0.49
    POSITIVE LOGITS
    enumi
    0.65
    ########.
    0.62
    xins
    0.57
    izen
    0.56
     שוליים
    0.55
     useAppContext
    0.55
     stuff
    0.54
    openzeppelin
    0.54
    ModelAdmin
    0.54
    adina
    0.53
    Act Density 0.183%

    No Known Activations