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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey official announcements or statements related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Valle
    -0.16
    SSID
    -0.15
     غر
    -0.14
     wart
    -0.14
    ews
    -0.14
     Barber
    -0.14
     Inflate
    -0.14
    381
    -0.14
     arg
    -0.14
    lords
    -0.13
    POSITIVE LOGITS
    erli
    0.16
    oux
    0.16
    enza
    0.15
    款
    0.15
    uron
    0.14
    chio
    0.14
    abbo
    0.14
    CTS
    0.14
    oftware
    0.14
    419
    0.14
    Act Density 0.211%

    No Known Activations