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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the pronoun 'me'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mb
    -0.67
    itton
    -0.62
     GC
    -0.62
     Niger
    -0.61
     Vendor
    -0.60
    DIV
    -0.60
    ysis
    -0.59
     Xavier
    -0.57
     Fellowship
    -0.56
     Mortal
    -0.56
    POSITIVE LOGITS
    aning
    1.26
    eting
    1.13
    asure
    1.12
    ans
    1.07
    asuring
    1.07
    anwhile
    0.99
    asured
    0.98
    asures
    0.95
    asts
    0.95
    chan
    0.91
    Act Density 0.160%

    No Known Activations