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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "me" indicating self-reference or personal perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.50
     Efq
    -1.36
     houſe
    -1.28
     Houſe
    -1.28
     '\\;'
    -1.27
     itſelf
    -1.26
     themſelves
    -1.25
     ſeveral
    -1.25
     Theſe
    -1.25
     purpoſe
    -1.19
    POSITIVE LOGITS
     Me
    1.44
     me
    1.35
     I
    1.24
    Me
    1.22
     ME
    1.12
    me
    0.99
     my
    0.98
     Myself
    0.94
    I
    0.92
     My
    0.88
    Act Density 0.040%

    No Known Activations