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

    Neuronpedia

    INDEX
    Explanations

    mentions of current events and politics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.82
     katun
    -0.63
     bambu
    -0.60
     lampa
    -0.57
     ekos
    -0.56
     jaya
    -0.56
     abstrak
    -0.56
     bahay
    -0.54
     pama
    -0.54
     bagay
    -0.53
    POSITIVE LOGITS
     indestru
    0.94
     unspeak
    0.86
     disreg
    0.82
     exorbit
    0.79
     shenan
    0.79
     inappro
    0.79
     ineffec
    0.79
     maneu
    0.78
     impra
    0.78
     indescri
    0.76
    Act Density 0.949%

    No Known Activations