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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political ideologies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Amen
    -0.81
     CJ
    -0.65
     adjoining
    -0.65
    itol
    -0.65
     Whe
    -0.63
    catentry
    -0.62
     Eleven
    -0.60
     Emir
    -0.60
    "}],"
    -0.60
    north
    -0.59
    POSITIVE LOGITS
    've
    1.05
    'd
    0.93
    're
    0.92
    'll
    0.92
    uristic
    0.81
     didn
    0.80
    pherd
    0.79
    miah
    0.73
     literally
    0.72
    self
    0.71
    Act Density 0.295%

    No Known Activations