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

    Neuronpedia

    INDEX
    Explanations

    terms related to reputation and public relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipar
    -0.15
    opian
    -0.15
    _PUS
    -0.15
    ssid
    -0.14
    æĺĮ
    -0.14
     treffen
    -0.14
    ubar
    -0.14
    icus
    -0.13
    ;charset
    -0.13
     öden
    -0.13
    POSITIVE LOGITS
     reput
    0.24
     reputation
    0.22
     Reputation
    0.20
    åĵģçīĮ
    0.19
     tarn
    0.19
     PR
    0.18
     Perception
    0.18
     perception
    0.18
     brand
    0.18
    image
    0.17
    Act Density 0.301%

    No Known Activations