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

    Neuronpedia

    INDEX
    Explanations

    terms related to conspiracy theories and political events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unceasing
    -0.79
     disregarding
    -0.78
     wilfully
    -0.77
     endeavouring
    -0.76
     unavoid
    -0.73
     ineffectual
    -0.72
     roused
    -0.71
     thoughtless
    -0.71
     mercurial
    -0.70
     languid
    -0.70
    POSITIVE LOGITS
     affez
    1.33
     meras
    1.27
     cyr
    1.23
     fré
    1.22
     utop
    1.22
     dises
    1.22
     alkoh
    1.21
     lapto
    1.21
     ideolog
    1.19
     kosme
    1.18
    Act Density 0.189%

    No Known Activations