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

    Neuronpedia

    INDEX
    Explanations

    beginning tokens that signal the start of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aparentemente
    -0.56
     supposedly
    -0.55
     oddly
    -0.54
     weirdly
    -0.53
     apparently
    -0.51
     clunky
    -0.51
    거나
    -0.50
    Typically
    -0.50
     Parece
    -0.49
     seems
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.82
     Congratulations
    0.78
     congratulations
    0.73
     достой
    0.69
    Congratulations
    0.69
     congratulated
    0.69
     cordially
    0.68
     heartily
    0.68
    serde
    0.67
     congratulate
    0.67
    Act Density 0.123%

    No Known Activations