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

    Neuronpedia

    INDEX
    Explanations

    words with the prefix "fr-" followed by various suffixes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "fr."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ROM
    -0.73
    LESS
    -0.69
     Protection
    -0.67
    WARE
    -0.67
    worth
    -0.67
    DOWN
    -0.65
     FTA
    -0.65
    WIND
    -0.64
     Reading
    -0.64
    Process
    -0.64
    POSITIVE LOGITS
    inges
    1.38
    iday
    1.15
    atern
    1.09
    anca
    1.07
    umpy
    1.03
    isco
    0.99
    ayed
    0.96
    angible
    0.95
    isson
    0.94
    idays
    0.93
    Act Density 0.023%

    No Known Activations