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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global issues or conflicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    esville
    -0.76
    vious
    -0.73
     Param
    -0.72
    reau
    -0.67
    ©¶æ
    -0.67
     Ralph
    -0.65
     Twe
    -0.63
    tein
    -0.62
     Refresh
    -0.60
    Wheel
    -0.59
    POSITIVE LOGITS
     envoy
    0.84
    heid
    0.81
    warming
    0.79
     ambassador
    0.75
     treaties
    0.74
     Consortium
    0.73
     diplomat
    0.72
     superpower
    0.72
    airs
    0.69
     currencies
    0.68
    Act Density 0.240%

    No Known Activations