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

    Neuronpedia

    INDEX
    Explanations

    specific sequences of capital letters that may form abbreviations or acronyms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the string "FR" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chio
    -0.90
    holder
    -0.85
    holders
    -0.84
    dress
    -0.79
    manship
    -0.74
    wealth
    -0.73
    lace
    -0.73
    iating
    -0.69
    sei
    -0.69
    estate
    -0.68
    POSITIVE LOGITS
    ONT
    1.19
    ESH
    1.11
    ANCE
    1.10
    ANK
    1.01
    ACTION
    0.98
    ugal
    0.93
    ANC
    0.92
    annie
    0.91
    AME
    0.91
    OST
    0.90
    Act Density 0.009%

    No Known Activations