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

    Neuronpedia

    INDEX
    Explanations

    references to roles and memberships in organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engl
    -0.16
    ople
    -0.16
    баÑĩ
    -0.15
    itar
    -0.15
    alama
    -0.15
    abin
    -0.14
    gni
    -0.14
    ÙĬÙĨÙĬ
    -0.14
    eki
    -0.14
    mlin
    -0.14
    POSITIVE LOGITS
    aven
    0.15
     Toy
    0.14
     conform
    0.14
     rocking
    0.14
     Con
    0.14
    IVERY
    0.13
     gif
    0.13
     tow
    0.13
     Fate
    0.13
     Eff
    0.13
    Act Density 0.026%

    No Known Activations