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

    Neuronpedia

    INDEX
    Explanations

    terms indicating significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oflavin
    -0.68
    resizingMask
    -0.67
     blisters
    -0.65
    зец
    -0.65
    ers
    -0.65
    ade
    -0.65
    er
    -0.64
     metropolitana
    -0.64
     viewType
    -0.63
    webElementXpaths
    -0.62
    POSITIVE LOGITS
     Important
    1.67
     important
    1.60
    Important
    1.57
    important
    1.49
     importance
    1.44
     Importance
    1.39
    Importance
    1.35
    importance
    1.32
     IMPORTANT
    1.30
    IMPORTANT
    1.29
    Act Density 0.087%

    No Known Activations