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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "~
    -0.20
     “
    -0.20
     reportedly
    -0.20
     “âĢ¦
    -0.20
     "...
    -0.19
     often
    -0.19
     "/
    -0.18
     "
    -0.18
     "..
    -0.18
     recently
    -0.17
    POSITIVE LOGITS
     thing
    0.34
     [
    0.33
     whole
    0.31
     guy
    0.28
     little
    0.26
     nice
    0.25
     really
    0.24
    whole
    0.23
    -[
    0.23
     guys
    0.23
    Act Density 0.446%

    No Known Activations