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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government policies and national security

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    enger
    -1.16
    MODE
    -1.12
    hou
    -1.08
    heet
    -1.06
    ttes
    -1.03
    furt
    -1.02
    oned
    -1.00
    bats
    -0.97
    oning
    -0.97
    hang
    -0.95
    POSITIVE LOGITS
     Geographic
    1.56
     Institutes
    1.38
    ity
    1.24
     Grid
    1.18
     Headquarters
    1.16
     Anthem
    1.15
     Rifle
    1.10
     Parks
    1.10
     Security
    1.09
     Institute
    1.08
    Act Density 0.394%

    No Known Activations