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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people or fictional characters

    oai_token-act-pair · gpt-3.5-turbo

    names and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clarity
    -0.74
     understandable
    -0.73
    ibaba
    -0.72
     contrast
    -0.68
    umph
    -0.66
    azeera
    -0.66
     reassuring
    -0.66
     Pwr
    -0.65
     emphasizing
    -0.63
    olulu
    -0.63
    POSITIVE LOGITS
     belonged
    1.28
     existed
    1.20
     had
    1.15
     hadn
    1.10
     resided
    1.10
     exists
    1.07
     belongs
    1.06
     was
    1.03
     originated
    1.02
     perished
    0.99
    Act Density 0.543%

    No Known Activations