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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific character names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     aen
    -1.81
     ftu
    -1.70
     mef
    -1.69
     fta
    -1.69
     fte
    -1.66
     „,
    -1.64
     sovere
    -1.59
     fatis
    -1.59
     wien
    -1.56
     thut
    -1.55
    POSITIVE LOGITS
    '
    0.85
    ’
    0.84
     who
    0.71
    ‘
    0.70
     during
    0.66
     before
    0.65
     via
    0.62
     about
    0.61
    ,
    0.61
     him
    0.60
    Act Density 0.517%

    No Known Activations