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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     more
    -0.63
     
    -0.63
     it
    -0.62
    .
    -0.62
     are
    -0.58
     I
    -0.58
      
    -0.57
    y
    -0.56
     a
    -0.55
    N
    -0.55
    POSITIVE LOGITS
    Portale
    1.25
     Efq
    1.14
    ########.
    1.12
    GEBURTSDATUM
    1.08
     Савезне
    1.08
     ―――――
    1.06
    IntoConstraints
    1.06
     AssemblyCompany
    1.03
     myſelf
    1.02
     للمعارف
    1.01
    Act Density 0.905%

    No Known Activations