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

    Neuronpedia

    INDEX
    Explanations

    sentences that discuss prioritizing personal interests over collective interests

    oai_token-act-pair · gpt-3.5-turbo

    the character "Ŀ."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awaru
    -0.67
     vitro
    -0.65
    ufact
    -0.65
     conception
    -0.64
     registration
    -0.63
     referen
    -0.63
     ponder
    -0.63
     plur
    -0.62
     endings
    -0.62
     presidents
    -0.62
    POSITIVE LOGITS
    bryce
    0.89
    ï¸ı
    0.89
    ĩ
    0.85
    Ĭ
    0.85
    ļ
    0.84
    ¯
    0.83
    ¼
    0.82
    Ŀ
    0.80
    £
    0.80
    İ
    0.79
    Act Density 0.185%

    No Known Activations