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

    Neuronpedia

    INDEX
    Explanations

    references to specific filmmakers and their styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    780
    -0.16
     Pap
    -0.15
     clam
    -0.15
     VOID
    -0.15
     EDGE
    -0.14
    ÙĬراÙĨ
    -0.14
    addle
    -0.14
    ician
    -0.14
    cco
    -0.14
    rag
    -0.14
    POSITIVE LOGITS
     Buffy
    0.34
     Cord
    0.33
     BUFF
    0.31
    BUFF
    0.31
    buff
    0.30
     Angel
    0.29
     Spike
    0.28
     buff
    0.28
     Giles
    0.28
     Buff
    0.26
    Act Density 0.006%

    No Known Activations