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

    Neuronpedia

    INDEX
    Explanations

    words related to security and protection

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    clerosis
    -0.42
    licks
    -0.41
    immer
    -0.40
    ibur
    -0.39
    ulz
    -0.38
    ynes
    -0.37
    kes
    -0.37
    Gray
    -0.35
    ettle
    -0.35
    immers
    -0.35
    POSITIVE LOGITS
     guarded
    0.49
     guarding
    0.46
     secrets
    0.39
     guard
    0.38
    ModLoader
    0.38
     duty
    0.37
     Passage
    0.37
     adolesc
    0.37
    cheon
    0.37
    Guard
    0.36
    Act Density 10.662%

    No Known Activations