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

    Neuronpedia

    INDEX
    Explanations

    HTML title tags and their attributes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     en
    -0.45
     owe
    -0.43
     (
    -0.43
    hbs
    -0.43
     ben
    -0.42
     
    -0.42
     har
    -0.42
    ,
    -0.42
     liquid
    -0.42
    会上
    -0.42
    POSITIVE LOGITS
     leaſt
    0.84
     occaf
    0.82
     cauſe
    0.82
    TypedDataSet
    0.81
     pleaſure
    0.80
     leſs
    0.79
     reaſon
    0.78
     purpoſe
    0.77
     صوتيه
    0.77
    存于互联网档案馆
    0.75
    Act Density 0.001%

    No Known Activations