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

    Neuronpedia

    INDEX
    Explanations

    first-person phrases discussing personal growth and life lessons

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    killed
    -0.73
    LOG
    -0.67
     %%
    -0.65
    username
    -0.64
    wine
    -0.63
    #$
    -0.61
    rose
    -0.60
     guiIcon
    -0.60
    pard
    -0.60
    ratulations
    -0.60
    POSITIVE LOGITS
     regards
    1.54
     relation
    1.40
     terms
    1.37
     regard
    1.32
     spite
    1.11
     favor
    1.10
    roads
    1.06
     lieu
    1.06
    clusions
    1.05
     conjunction
    1.00
    Act Density 0.325%

    No Known Activations