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

    Neuronpedia

    INDEX
    Explanations

    terms associated with statistical or mathematical positivity and categories or groupings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lowest
    -0.63
     lower
    -0.54
    imp
    -0.53
     down
    -0.53
     bottom
    -0.52
     below
    -0.52
     ниже
    -0.51
    avedra
    -0.49
     basement
    -0.48
     reduced
    -0.47
    POSITIVE LOGITS
    PositiveButton
    0.87
     onResume
    0.86
     BoxDecoration
    0.81
     OnEnable
    0.79
    OnAdd
    0.79
     upvote
    0.77
    }_{+
    0.77
    Positives
    0.77
    SuccessListener
    0.76
    onResume
    0.75
    Act Density 1.487%

    No Known Activations