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

    Neuronpedia

    INDEX
    Explanations

    the name "Gordon" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etu
    -0.17
    nej
    -0.16
    olation
    -0.16
     Ku
    -0.15
    atoi
    -0.15
    itia
    -0.15
    illery
    -0.14
    anning
    -0.14
    sst
    -0.14
    æĮ¯
    -0.14
    POSITIVE LOGITS
    swer
    0.20
    wart
    0.17
    ziej
    0.16
    ign
    0.16
    vale
    0.16
    mixed
    0.15
    Others
    0.15
    iag
    0.14
    éné
    0.14
    enthal
    0.14
    Act Density 0.005%

    No Known Activations