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

    Neuronpedia

    INDEX
    Explanations

    character sequences related to the abbreviation "FR"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "FR" or formatting markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chio
    -0.82
    dress
    -0.80
    holders
    -0.79
    iating
    -0.77
    holder
    -0.76
    hern
    -0.71
     Hots
    -0.70
    wealth
    -0.70
    lace
    -0.69
    manship
    -0.68
    POSITIVE LOGITS
    ONT
    1.25
    ANCE
    1.11
    ESH
    1.06
    ugal
    0.98
    ACTION
    0.98
    ANK
    0.94
    annie
    0.92
    ANC
    0.90
    AME
    0.90
    OST
    0.87
    Act Density 0.014%

    No Known Activations