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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political statements and endorsements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.71
    kw
    -0.68
     Kut
    -0.65
    iaries
    -0.65
    Shot
    -0.64
    eka
    -0.64
    holder
    -0.61
     suspic
    -0.61
     Shot
    -0.61
    cephal
    -0.61
    POSITIVE LOGITS
    izu
    0.68
     ie
    0.66
    ushima
    0.65
    [
    0.65
    /"
    0.62
    ocumented
    0.61
     "$:/
    0.60
    jriwal
    0.59
     Mao
    0.58
     (£
    0.57
    Act Density 0.068%

    No Known Activations