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

    Neuronpedia

    INDEX
    Explanations

    instances of embarrassing or inappropriate behavior

    oai_token-act-pair · gpt-3.5-turbo

    instances of embarrassment or awkward social situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $.
    -0.60
    AAA
    -0.60
    .):
    -0.58
    /,
    -0.57
    AAAA
    -0.56
    %,
    -0.55
    .),
    -0.55
     decentralized
    -0.54
     Regist
    -0.54
    $,
    -0.53
    POSITIVE LOGITS
     during
    1.26
     onstage
    1.15
     when
    1.00
     whilst
    0.96
     backstage
    0.93
    during
    0.91
     midway
    0.88
     whenever
    0.87
     after
    0.85
     while
    0.82
    Act Density 0.818%

    No Known Activations