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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political, social, and economic issues being discussed or debated

    oai_token-act-pair · gpt-3.5-turbo

    references to systemic issues or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Negro
    -0.74
     strugg
    -0.70
     regist
    -0.68
     notor
    -0.67
     ende
    -0.66
     ponder
    -0.65
     snail
    -0.65
     adm
    -0.65
     jugg
    -0.65
     sacrific
    -0.65
    POSITIVE LOGITS
    ï¸ı
    1.03
    ¯
    1.02
    ï¸
    0.85
    cue
    0.84
    STEM
    0.84
    âĢł
    0.84
    âģ
    0.80
    east
    0.79
    efe
    0.79
    rh
    0.78
    Act Density 0.190%

    No Known Activations