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

    Neuronpedia

    INDEX
    Explanations

    information related to crime, law enforcement, and incidents of violence

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    fortunately
    -0.53
    henko
    -0.53
    lycer
    -0.53
    cffffcc
    -0.52
    jri
    -0.50
    ieri
    -0.50
    twitter
    -0.48
    Nin
    -0.47
    949
    -0.47
     theorem
    -0.47
    POSITIVE LOGITS
     these
    0.61
     either
    0.59
     this
    0.57
     interacting
    0.56
     such
    0.54
     various
    0.53
     cryptocurrencies
    0.52
     CoC
    0.52
     potentially
    0.52
     each
    0.51
    Act Density 5.142%

    No Known Activations