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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social events, including terms related to global affairs and governmental actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    jee
    -0.57
    axe
    -0.55
    mong
    -0.53
     oranges
    -0.53
    wash
    -0.52
    bits
    -0.52
    eat
    -0.52
    wright
    -0.51
    fully
    -0.51
     untreated
    -0.51
    POSITIVE LOGITS
     Sanctuary
    0.60
     Headquarters
    0.60
     sanctuary
    0.60
     headquarters
    0.58
     perimeter
    0.56
     alliances
    0.56
     acad
    0.56
     reserve
    0.55
     permanent
    0.55
     embassy
    0.55
    Act Density 12.794%

    No Known Activations