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

    Neuronpedia

    INDEX
    Explanations

    references to international agreements or diplomatic deals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idge
    -0.15
    strap
    -0.15
    aje
    -0.15
     endings
    -0.14
    ikip
    -0.14
    endas
    -0.14
    bat
    -0.14
     Gri
    -0.14
     unde
    -0.13
    els
    -0.13
    POSITIVE LOGITS
    岸
    0.18
    rita
    0.16
     Carbon
    0.16
     carbon
    0.16
    Fade
    0.15
    arbon
    0.15
     flick
    0.15
    Carbon
    0.14
    èŃ
    0.14
    Å¡ÃŃm
    0.14
    Act Density 0.076%

    No Known Activations