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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts and voting information in a list format, likely related to a ranking or competition

    oai_token-act-pair · gpt-3.5-turbo

    various formats of parentheses and their accompanying numerical values or votes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zuckerberg
    -0.61
     longer
    -0.59
     Guth
    -0.56
     Blumenthal
    -0.56
     Mn
    -0.55
     multim
    -0.55
     Purpose
    -0.55
    SR
    -0.55
     Pruitt
    -0.55
    andum
    -0.54
    POSITIVE LOGITS
    aho
    0.79
    fourth
    0.72
    grave
    0.69
    interstitial
    0.69
    nine
    0.68
    æ©
    0.68
    english
    0.66
    ãģ£
    0.64
    eight
    0.63
    æĸ
    0.63
    Act Density 0.063%

    No Known Activations