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

    Neuronpedia

    INDEX
    Explanations

    political terms and names related to libertarianism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -0.89
     impra
    -0.84
     shenan
    -0.79
     encomp
    -0.78
     ineffec
    -0.78
     unspeak
    -0.75
     apprehen
    -0.74
     fath
    -0.73
     vainly
    -0.73
     strick
    -0.73
    POSITIVE LOGITS
     mercen
    0.72
     democra
    0.69
     prostitu
    0.68
    aibo
    0.62
     guir
    0.62
     hial
    0.62
     tappa
    0.60
     elef
    0.60
     distanciation
    0.59
     masaj
    0.59
    Act Density 0.571%

    No Known Activations