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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that indicate exceptions or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    клопе
    -0.70
    ::_('
    -0.62
    hyrchwyd
    -0.60
    qrstuvwxyz
    -0.58
    </caption>
    -0.57
    efeated
    -0.56
    怎么办
    -0.55
    orsese
    -0.55
     etc
    -0.54
     etti
    -0.54
    POSITIVE LOGITS
    Though
    1.00
    Although
    0.96
     Meski
    0.96
    Meski
    0.95
     Though
    0.94
     Embora
    0.92
     Although
    0.89
     embora
    0.86
     though
    0.85
    While
    0.85
    Act Density 0.156%

    No Known Activations