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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Fr" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the French language or culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Twain
    -0.87
    eers
    -0.82
    eering
    -0.67
     Blazers
    -0.66
     Archdemon
    -0.66
    >[
    -0.66
    lihood
    -0.65
    6666
    -0.65
    eer
    -0.64
    ãĥŁ
    -0.64
    POSITIVE LOGITS
    ictional
    0.95
    aternity
    0.93
    aternal
    0.92
    umpy
    0.92
     Fr
    0.90
    annie
    0.89
    inge
    0.89
    antz
    0.88
    Fr
    0.87
    atell
    0.86
    Act Density 0.006%

    No Known Activations