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

    Neuronpedia

    INDEX
    Explanations

    references to the cast of films or shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    гов
    -0.15
    laus
    -0.15
    ously
    -0.15
    erable
    -0.15
    asion
    -0.15
    ubb
    -0.14
    erea
    -0.14
    adx
    -0.14
    arpa
    -0.14
     Slee
    -0.14
    POSITIVE LOGITS
    kowski
    0.15
    ureau
    0.15
     Unidos
    0.14
    ık
    0.14
    ers
    0.14
    .localization
    0.14
    rol
    0.13
    role
    0.13
    gro
    0.13
    -*-
    0.13
    Act Density 0.021%

    No Known Activations