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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "From what" and "what I can" or "we can" indicating making observations or inferences

    oai_token-act-pair · gpt-3.5-turbo

    references to personal observations and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.60
    powers
    -0.58
    AND
    -0.58
    deals
    -0.57
     grandchildren
    -0.54
    ãĤ³
    -0.54
    èĢħ
    -0.53
    ]=
    -0.52
     Flavoring
    -0.52
    å°Ĩ
    -0.52
    POSITIVE LOGITS
     we
    1.15
     I
    1.03
     seen
    0.90
     pictured
    0.90
    liest
    0.86
     ours
    0.83
     you
    0.81
     imaginable
    0.80
     discussed
    0.79
     mentioned
    0.79
    Act Density 0.484%

    No Known Activations