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

    Neuronpedia

    INDEX
    Explanations

    references to specific fictional characters and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SafeMath
    -0.56
    Архівовано
    -0.51
     الدولى
    -0.50
    DebuggerNonUser
    -0.49
     assic
    -0.49
    EMENTS
    -0.49
    펴
    -0.48
     beban
    -0.48
    herin
    -0.48
    Exciting
    -0.48
    POSITIVE LOGITS
     canon
    0.98
    canon
    0.86
     canonical
    0.76
     backstory
    0.75
     lore
    0.73
     voiced
    0.73
     portrayal
    0.70
     ingame
    0.70
    ◊
    0.70
     reused
    0.69
    Act Density 0.704%

    No Known Activations