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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gian
    -0.73
    wine
    -0.64
    edly
    -0.63
    raid
    -0.61
    iced
    -0.60
    #$
    -0.60
    akia
    -0.59
    anza
    -0.58
    SHIP
    -0.57
    cloth
    -0.55
    POSITIVE LOGITS
     regards
    1.21
     regard
    1.02
     terms
    0.94
     spite
    0.86
     nutshell
    0.83
     lieu
    0.81
     relation
    0.80
     perpet
    0.80
    clus
    0.80
     teasp
    0.79
    Act Density 0.462%

    No Known Activations