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

    Neuronpedia

    INDEX
    Explanations

    elements related to plot twists and narrative surprises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anship
    -0.15
    åĨµ
    -0.15
    _IV
    -0.14
    anco
    -0.14
     buc
    -0.14
    adla
    -0.14
    èĮĥ
    -0.14
    anes
    -0.13
     célib
    -0.13
    ernote
    -0.13
    POSITIVE LOGITS
    etak
    0.14
    ãģ®ãģĮ
    0.14
    unas
    0.14
    ward
    0.14
    _MAJOR
    0.14
    важа
    0.14
     Tie
    0.13
     tie
    0.13
    åIJij
    0.13
    TEGER
    0.13
    Act Density 0.086%

    No Known Activations