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

    Neuronpedia

    INDEX
    Explanations

    references to laws, regulations, or governance related to countries and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itat
    -0.15
     اÙĦØŃÙĬ
    -0.15
    ensch
    -0.15
    tura
    -0.14
     himself
    -0.14
    acula
    -0.14
    itta
    -0.14
    rain
    -0.13
    enstein
    -0.13
    ObjectOfType
    -0.13
    POSITIVE LOGITS
     themselves
    0.21
    ouden
    0.16
    kes
    0.16
     reput
    0.15
     alike
    0.14
     their
    0.14
    outine
    0.14
    ridor
    0.14
     programm
    0.14
    ounder
    0.13
    Act Density 0.267%

    No Known Activations