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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political opinions and policy discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to American political themes and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.82
    etheless
    -0.72
    ItemTracker
    -0.71
    76561
    -0.67
     Annotations
    -0.67
     FIG
    -0.67
    ĸļ
    -0.66
    PF
    -0.64
    ¶
    -0.62
     References
    -0.61
    POSITIVE LOGITS
     âĢ¦"
    1.23
     ..."
    1.16
    .'"
    1.07
    ,'"
    1.06
    .")
    1.03
    .""
    0.98
    !"
    0.97
    âĢ¦"
    0.96
    ."[
    0.95
    "—
    0.95
    Act Density 1.240%

    No Known Activations