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

    Neuronpedia

    INDEX
    Explanations

    words related to politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uteur
    -0.18
    iyet
    -0.17
    ertas
    -0.16
    å¢ĥ
    -0.15
    ez
    -0.15
    ênh
    -0.15
    eson
    -0.15
    cit
    -0.14
    ungal
    -0.14
    ighet
    -0.14
    POSITIVE LOGITS
     correct
    0.23
     Correct
    0.21
     incorrect
    0.21
    correct
    0.21
    icians
    0.20
     correctness
    0.19
     Incorrect
    0.18
    .correct
    0.17
    incorrect
    0.17
    ically
    0.17
    Act Density 0.007%

    No Known Activations