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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or notations involving parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <i>
    -0.68
    ț
    -0.67
     onCancelled
    -0.66
     Frankel
    -0.66
     branches
    -0.65
    ticals
    -0.64
     books
    -0.62
    
    -0.61
    ymce
    -0.61
    books
    -0.60
    POSITIVE LOGITS
     themſelves
    1.15
     raiſ
    1.13
     pleaſure
    1.12
     myſelf
    1.11
     Monfieur
    1.11
     Anſ
    1.09
     Shakspeare
    1.08
     anſ
    1.05
     uſed
    1.05
    ագրություններ
    1.04
    Act Density 0.653%

    No Known Activations