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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "me" or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.55
     Efq
    -1.42
     Houſe
    -1.37
     houſe
    -1.35
     Theſe
    -1.34
     ſeveral
    -1.32
     itſelf
    -1.31
     themſelves
    -1.27
     purpoſe
    -1.26
     Anſ
    -1.22
    POSITIVE LOGITS
     Me
    1.51
     me
    1.41
     I
    1.34
    Me
    1.26
     ME
    1.18
     Myself
    1.04
     my
    1.03
    I
    0.99
     My
    0.97
    me
    0.97
    Act Density 0.040%

    No Known Activations