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

    Neuronpedia

    INDEX
    Explanations

    conspiratorial and anti-establishment rhetoric, particularly regarding the idea of betrayal and secrecy in society

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.74
    etheless
    -0.70
     Hurricanes
    -0.68
    utenberg
    -0.68
     Pione
    -0.66
     destro
    -0.66
     trave
    -0.66
    eus
    -0.64
     Sapp
    -0.64
     constitu
    -0.64
    POSITIVE LOGITS
    ings
    1.76
    able
    1.66
    ables
    1.59
    ability
    1.40
    backs
    1.31
    ers
    1.28
    aways
    1.25
    away
    1.20
    outs
    1.18
    ership
    1.13
    Act Density 18.466%

    No Known Activations