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

    Neuronpedia

    INDEX
    Explanations

    numbers and comparative phrases that indicate quantity or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jutaan
    -0.51
     kolei
    -0.51
    posób
    -0.51
    omiast
    -0.51
     zugleich
    -0.50
    ího
    -0.49
     doua
    -0.49
    bootstrapcdn
    -0.49
     millions
    -0.49
     Meksiku
    -0.49
    POSITIVE LOGITS
     dozen
    1.46
    dozen
    1.21
     dozens
    1.07
     doz
    1.00
     score
    0.96
     scores
    0.93
     Score
    0.86
    score
    0.84
     Do
    0.84
     CreateTagHelper
    0.83
    Act Density 0.345%

    No Known Activations