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

    Neuronpedia

    INDEX
    Explanations

    words related to public figures and political scandals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     although
    -0.28
     Hels
    -0.28
    !.
    -0.27
     Pearce
    -0.27
     ASAP
    -0.27
    iverpool
    -0.27
     Kak
    -0.27
     Beir
    -0.27
    outube
    -0.27
     tonight
    -0.26
    POSITIVE LOGITS
     persists
    0.39
    pires
    0.39
     becomes
    0.39
     behaves
    0.39
     disappears
    0.39
     has
    0.39
     cannot
    0.38
     loses
    0.37
     seemed
    0.37
     retains
    0.37
    Act Density 28.497%

    No Known Activations