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

    Neuronpedia

    INDEX
    Explanations

    pronouns and phrases indicating direct address to the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mayer
    -0.17
    odash
    -0.15
     VÅ¡ech
    -0.15
    ãĥ³ãĤ¯
    -0.14
    ì§Ŀ
    -0.14
     ÄĮer
    -0.14
    ubi
    -0.14
    jax
    -0.14
    renom
    -0.14
    Ñĥже
    -0.13
    POSITIVE LOGITS
     debt
    0.22
     surely
    0.20
     definitely
    0.20
     simply
    0.18
     Debt
    0.18
     certainly
    0.17
     debts
    0.17
     definite
    0.17
    _defs
    0.17
     sure
    0.16
    Act Density 0.059%

    No Known Activations