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

    Neuronpedia

    INDEX
    Explanations

    statements of existence or identity concerning individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blech
    -0.55
    τέλε
    -0.53
     sufficiente
    -0.51
    Unione
    -0.49
    our
    -0.49
    Dni
    -0.48
     sami
    -0.48
    Dzi
    -0.48
     Huss
    -0.48
    onshire
    -0.47
    POSITIVE LOGITS
     himself
    1.29
    himself
    1.03
     Himself
    0.97
     his
    0.96
    的他
    0.87
     He
    0.83
     he
    0.77
     His
    0.75
     HIM
    0.75
    parsedMessage
    0.72
    Act Density 0.445%

    No Known Activations