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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their distribution in numerical sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mijne
    -0.70
     indígen
    -0.60
     enfans
    -0.58
     queſta
    -0.57
     nemico
    -0.54
    -------------</
    -0.51
     Италијани
    -0.50
    şört
    -0.49
     travailleurs
    -0.49
     étoient
    -0.47
    POSITIVE LOGITS
     etc
    0.53
     Norton
    0.49
     Big
    0.48
    0.48
     Etc
    0.48
    etc
    0.48
     Aux
    0.47
    hatic
    0.47
    ect
    0.47
                
    0.47
    Act Density 0.383%

    No Known Activations