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

    Neuronpedia

    INDEX
    Explanations

    references to writers and directors in the context of their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cinder
    -0.16
    оÑĢе
    -0.16
     Gaw
    -0.15
    егоÑĢ
    -0.15
    иÑģÑĤÑĢа
    -0.14
    qml
    -0.14
     Beard
    -0.14
    TestCategory
    -0.14
    sst
    -0.14
    hop
    -0.14
    POSITIVE LOGITS
     Buffy
    0.36
     BUFF
    0.29
    BUFF
    0.27
     Giles
    0.24
    _BUFF
    0.23
     Buff
    0.23
    buff
    0.22
     Slayer
    0.22
     buff
    0.22
     Vampire
    0.19
    Act Density 0.014%

    No Known Activations