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

    Neuronpedia

    INDEX
    Explanations

    blocks of consistent data or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.80
     Efq
    -0.72
     Anſ
    -0.66
     Monfieur
    -0.65
     stomat
    -0.64
     Ibidem
    -0.64
     photolibrary
    -0.63
     tdci
    -0.63
    ENODEV
    -0.63
     iprot
    -0.62
    POSITIVE LOGITS
       
    1.80
         
    1.16
               
    1.04
             
    1.03
                   
    0.92
     
    0.91
                               
    0.90
                     
    0.86
                 
    0.85
                       
    0.82
    Act Density 0.304%

    No Known Activations