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

    Neuronpedia

    INDEX
    Explanations

    references to community events and interactions among participants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     written
    -0.19
    寫
    -0.18
    åĨĻ
    -0.18
    written
    -0.16
     Written
    -0.16
    argas
    -0.15
     Writing
    -0.15
    iveness
    -0.15
     напиÑģ
    -0.14
     writ
    -0.14
    POSITIVE LOGITS
     address
    0.22
    address
    0.20
    Address
    0.19
     briefly
    0.19
     pref
    0.19
     explan
    0.19
     Address
    0.18
     introdu
    0.18
     Audience
    0.18
     tell
    0.18
    Act Density 0.117%

    No Known Activations