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

    Neuronpedia

    INDEX
    Explanations

    terms related to social dynamics and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.35
     (“
    -0.34
     “âĢ¦
    -0.28
     âĢŀ
    -0.28
     “[
    -0.28
     ãĢĮ
    -0.23
     «
    -0.21
     ``
    -0.21
    =”
    -0.20
     («
    -0.20
    POSITIVE LOGITS
    "
    0.40
    ",
    0.30
    "'
    0.25
    "/
    0.23
    ”
    0.23
    []"
    0.23
    ":
    0.22
    ()"
    0.22
    ãĢįãģ®
    0.21
    ","
    0.21
    Act Density 0.395%

    No Known Activations