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

    Neuronpedia

    INDEX
    Explanations

    phrases related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the symbol "Ļ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yield
    -0.68
     pyramid
    -0.67
     logger
    -0.66
     rank
    -0.65
     interest
    -0.63
     opportunities
    -0.63
     retreat
    -0.62
     western
    -0.62
     prostitute
    -0.61
     advantages
    -0.60
    POSITIVE LOGITS
    ï¸ı
    1.37
    _>
    1.08
    ski
    0.94
    Balt
    0.93
    ï¸
    0.92
    STEM
    0.88
     implying
    0.87
    something
    0.85
    £
    0.85
    except
    0.85
    Act Density 0.224%

    No Known Activations