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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "demon" or variations of it

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ippi
    -0.64
    IGH
    -0.59
    RAFT
    -0.57
     Seym
    -0.56
    å
    -0.54
     Opportun
    -0.53
    aird
    -0.52
    ills
    -0.52
     proble
    -0.52
     Soda
    -0.52
    POSITIVE LOGITS
    stration
    1.10
    iac
    0.92
    ises
    0.80
    ising
    0.79
    ormal
    0.79
    oid
    0.75
    strate
    0.73
    izing
    0.73
    izes
    0.72
    ization
    0.72
    Act Density 7.752%

    No Known Activations