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

    Neuronpedia

    INDEX
    Explanations

    characters' names as well as themes of sci-fi or action narrative passages

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ablishment
    -0.41
    upon
    -0.38
     Belief
    -0.36
     Petraeus
    -0.33
    hovah
    -0.32
    affles
    -0.32
    Ö¼
    -0.31
     liar
    -0.31
     Journalists
    -0.30
    enance
    -0.30
    POSITIVE LOGITS
    eties
    0.49
    ãĥ¼ãĤ¯
    0.46
     Skywalker
    0.43
    ny
    0.43
    itus
    0.42
    strument
    0.42
    sson
    0.42
    sha
    0.42
    avin
    0.42
    eteenth
    0.41
    Act Density 9.423%

    No Known Activations