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

    Neuronpedia

    INDEX
    Explanations

    references to unidentified aerial phenomena and potential threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    碼
    -0.17
    coil
    -0.16
    Collapsed
    -0.16
    arga
    -0.15
    yscale
    -0.14
     teleport
    -0.14
    άνα
    -0.14
    _DEPRECATED
    -0.14
    oble
    -0.13
    alloca
    -0.13
    POSITIVE LOGITS
     altitude
    0.23
     craft
    0.23
    craft
    0.20
     crafts
    0.19
     flew
    0.19
     radar
    0.18
     fly
    0.18
     flying
    0.18
     buzzing
    0.18
     buzz
    0.17
    Act Density 0.063%

    No Known Activations