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

    Neuronpedia

    INDEX
    Explanations

    elements related to role-playing and simulations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atego
    -0.15
    ços
    -0.15
    ris
    -0.15
    loi
    -0.14
    pong
    -0.14
    ldkf
    -0.14
    /sdk
    -0.14
    rado
    -0.14
    cela
    -0.14
     Throne
    -0.13
    POSITIVE LOGITS
     fict
    0.29
     fictional
    0.24
     simulated
    0.21
     imaginary
    0.19
     pretended
    0.19
     hypothetical
    0.19
     mock
    0.18
     pretend
    0.17
     Fiction
    0.17
     Mock
    0.16
    Act Density 0.311%

    No Known Activations