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

    Neuronpedia

    INDEX
    Explanations

    names of actors and film industry-related figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eya
    -0.18
    ãĥ¬ãĥ¼
    -0.15
    angi
    -0.14
    asan
    -0.14
    OMPI
    -0.14
    esi
    -0.14
    endif
    -0.14
    yb
    -0.14
    srv
    -0.14
    eldorf
    -0.14
    POSITIVE LOGITS
    ynos
    0.14
    ivate
    0.14
     nich
    0.14
     dint
    0.14
    /ml
    0.14
    andler
    0.14
    bach
    0.14
    arbon
    0.13
     عÙĦÙĬÙĩ
    0.13
    ynth
    0.13
    Act Density 0.014%

    No Known Activations