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

    Neuronpedia

    INDEX
    Explanations

    the preposition "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WaitGroup
    -0.67
    //
    -0.52
    >");
    -0.51
     Z
    -0.50
    thâu
    -0.50
     AssemblyCompany
    -0.50
     grund
    -0.49
    _));
    -0.48
    Rüyada
    -0.47
     S
    -0.46
    POSITIVE LOGITS
     itſelf
    0.85
     Majefty
    0.77
     Anſ
    0.77
     faſt
    0.77
     purpoſe
    0.76
     houſe
    0.71
     themſelves
    0.71
     myſelf
    0.71
     ſche
    0.71
     Wallflower
    0.70
    Act Density 0.001%

    No Known Activations