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

    Neuronpedia

    INDEX
    Explanations

    references to significant historical events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Napoleon
    -0.20
     Vatican
    -0.15
    ILINE
    -0.14
     bì
    -0.14
    using
    -0.14
    enstein
    -0.14
    عر
    -0.14
    SWEP
    -0.14
    azi
    -0.14
    ursal
    -0.14
    POSITIVE LOGITS
     Plymouth
    0.29
     Pur
    0.29
     Colony
    0.27
     Pil
    0.27
    162
    0.27
     colony
    0.27
    163
    0.24
     Jame
    0.23
    164
    0.23
    165
    0.23
    Act Density 0.016%

    No Known Activations