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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating absence or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RESS
    -0.17
    ilon
    -0.16
     Simpson
    -0.15
    ermal
    -0.15
    olution
    -0.15
    antan
    -0.15
    hai
    -0.14
    iliar
    -0.14
    ugu
    -0.14
     whenever
    -0.13
    POSITIVE LOGITS
     proper
    0.19
    ypi
    0.16
    edException
    0.16
     properly
    0.16
    acher
    0.16
    abox
    0.15
    ritz
    0.15
    ç»ıè¿ĩ
    0.15
    479
    0.15
    Without
    0.15
    Act Density 0.021%

    No Known Activations