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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and numerical values related to measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     twenty
    -0.50
     Twenty
    -0.49
    Twenty
    -0.47
     ten
    -0.45
     TWENTY
    -0.44
     veinte
    -0.44
    twenty
    -0.44
     thirty
    -0.41
    Thirty
    -0.38
    Tikang
    -0.38
    POSITIVE LOGITS
    ScopeManager
    0.75
     ½
    0.72
     ¾
    0.68
     snippetHide
    0.68
    :✨
    0.67
     externi
    0.66
    0.62
    ("")]
    0.61
    tagHelper
    0.61
    half
    0.59
    Act Density 0.968%

    No Known Activations