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

    Neuronpedia

    INDEX
    Explanations

    references to competitive achievements and record-setting events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     society
    -0.15
     Lebens
    -0.14
    ibri
    -0.14
    кап
    -0.14
    iele
    -0.13
     ↵↵
    -0.13
    Pitch
    -0.13
    pub
    -0.13
    _Context
    -0.13
    /connect
    -0.13
    POSITIVE LOGITS
     conservatism
    0.17
    éļ
    0.16
     Conserv
    0.15
     podium
    0.14
    xico
    0.14
    vest
    0.14
     prer
    0.14
    лаÑģ
    0.14
     Mentor
    0.14
    stalk
    0.14
    Act Density 0.120%

    No Known Activations