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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences or feelings related to "me."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.17
    rous
    -0.16
    HING
    -0.16
    ashtra
    -0.15
    oard
    -0.15
    rente
    -0.14
    net
    -0.14
    ayd
    -0.14
    ستÙħ
    -0.14
     maybe
    -0.14
    POSITIVE LOGITS
    /us
    0.19
    inerary
    0.16
    itable
    0.16
    zelf
    0.15
    SELF
    0.15
    andering
    0.15
    -même
    0.15
    elf
    0.15
    zzo
    0.14
    athed
    0.14
    Act Density 0.071%

    No Known Activations