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

    Neuronpedia

    INDEX
    Explanations

    mentions of espionage-related terms and laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.52
    /**
    -0.82
    
    -0.79
    <?
    -0.78
     endeavoured
    -0.74
    ⓧ
    -0.68
     endow
    -0.68
     chanced
    -0.67
     harmonize
    -0.67
     endeavored
    -0.67
    POSITIVE LOGITS
     Esp
    1.14
    Esp
    1.06
     Sp
    0.94
    Sp
    0.93
     ESP
    0.92
     Spe
    0.91
    ESP
    0.89
     esp
    0.89
     SP
    0.84
    esp
    0.83
    Act Density 0.087%

    No Known Activations