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

    Neuronpedia

    INDEX
    Explanations

    indicators of statistical or scientific analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.82
     (“
    -0.66
    /
    -0.65
     (
    -0.62
     ("
    -0.62
     obviously
    -0.61
    ↵
    -0.60
          
    -0.60
     essentially
    -0.60
        
    -0.58
    POSITIVE LOGITS
    .*")]
    0.96
     XNUMX
    0.96
     houſe
    0.96
    NUMX
    0.92
     varandra
    0.91
     myſelf
    0.89
     تانيه
    0.89
    ^(@)
    0.88
     tjän
    0.85
     femininas
    0.83
    Act Density 0.019%

    No Known Activations