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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns emphasizing personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.93
     Beſ
    -0.84
     Eſ
    -0.79
     Monfieur
    -0.76
     Reſ
    -0.75
     Võ
    -0.75
     ſeveral
    -0.74
     Diſ
    -0.73
     themſelves
    -0.70
     Padang
    -0.69
    POSITIVE LOGITS
     I
    1.86
    I
    1.41
     my
    1.04
     My
    1.03
     miei
    0.96
     i
    0.95
    IOUtils
    0.89
     myself
    0.88
     Myself
    0.87
     я
    0.86
    Act Density 0.237%

    No Known Activations