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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "wrap" and its variations, including "wrapping" and "wrapped."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.78
    RenderAtEndOf
    -0.61
    Hozzáférés
    -0.60
    bewerken
    -0.60
     []:
    -0.58
    isContained
    -0.55
    WindowConstants
    -0.55
    LookAnd
    -0.53
     فريبيس
    -0.52
     irré
    -0.51
    POSITIVE LOGITS
     wrap
    1.02
     embracing
    1.02
     wraps
    0.98
     Wraps
    0.97
    wraps
    0.96
     Wrap
    0.94
     wrapping
    0.94
    wrapping
    0.90
     embrace
    0.89
    Wrap
    0.87
    Act Density 0.120%

    No Known Activations