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

    Neuronpedia

    INDEX
    Explanations

    individuals associated with specific interests or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to fandoms or fan culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CVE
    -0.63
    ".[
    -0.62
    .''.
    -0.61
     '.
    -0.58
    aughs
    -0.57
    ãĥł
    -0.57
    ."[
    -0.54
    ]);
    -0.54
    ophon
    -0.54
    %).
    -0.53
    POSITIVE LOGITS
     yourself
    1.29
     you
    1.11
     please
    1.11
     your
    1.06
     yourselves
    1.05
     PLEASE
    1.05
     then
    1.02
     THEN
    1.01
    you
    0.90
    your
    0.87
    Act Density 0.402%

    No Known Activations