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

    Neuronpedia

    INDEX
    Explanations

    the word "older".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <em>
    -0.87
     
    -0.85
    </em>
    -0.81
     I
    -0.80
    </strong>
    -0.77
    <strong>
    -0.76
     “
    -0.76
     la
    -0.74
      
    -0.71
     am
    -0.71
    POSITIVE LOGITS
     Monfieur
    1.44
     myſelf
    1.40
     Theſe
    1.38
     Houſe
    1.34
     itſelf
    1.34
     photolibrary
    1.29
     Diſ
    1.28
     pleaſure
    1.28
    ſelves
    1.27
    ſelf
    1.26
    Act Density 0.006%

    No Known Activations