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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -1.20
    IntoConstraints
    -1.08
     OkHttpClient
    -1.02
     للمعارف
    -1.01
    protoimpl
    -1.01
    ſelves
    -1.00
     nahilalakip
    -1.00
    MethodManager
    -0.99
     defaultstate
    -0.99
     فريبيس
    -0.96
    POSITIVE LOGITS
     it
    0.85
     you
    0.84
     they
    0.79
     there
    0.72
     we
    0.69
     that
    0.68
     because
    0.62
    ,
    0.62
     I
    0.61
     people
    0.61
    Act Density 0.390%

    No Known Activations