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

    Neuronpedia

    INDEX
    Explanations

    the word "too" and variations of its usage, particularly indicating excessiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     שוליים
    -0.60
    COLN
    -0.52
    riften
    -0.50
    
    -0.46
    Билгалдахарш
    -0.43
    inSlope
    -0.42
     EconPapers
    -0.42
     fieltro
    -0.42
    cartera
    -0.42
     titoli
    -0.42
    POSITIVE LOGITS
     too
    0.89
     Too
    0.84
    Too
    0.82
    too
    0.82
     portable
    0.69
     TOO
    0.64
    太
    0.62
     overly
    0.60
    TOO
    0.59
     demasiado
    0.58
    Act Density 0.277%

    No Known Activations