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

    Neuronpedia

    INDEX
    Explanations

    keywords related to social issues and community actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .",↵
    -0.18
    -0.18
    -0.17
    .',↵
    -0.17
    ãĢĤ",↵
    -0.15
     toe
    -0.15
    "];↵
    -0.15
     Burton
    -0.15
     $.
    -0.14
    _.
    -0.14
    POSITIVE LOGITS
    ")
    0.25
    "),
    0.24
    ”)
    0.24
    ”),
    0.23
     "')
    0.22
    ")(
    0.22
    »)
    0.21
    >>)
    0.21
    "/
    0.20
    ")),
    0.20
    Act Density 0.032%

    No Known Activations