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

    Neuronpedia

    INDEX
    Explanations

    names and titles of individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.82
     appre
    -0.77
     wheelchair
    -0.72
    orph
    -0.71
     unden
    -0.70
     actionGroup
    -0.68
    obyl
    -0.68
     skelet
    -0.67
    comed
    -0.66
     veterinary
    -0.65
    POSITIVE LOGITS
     Hyde
    0.96
     Claus
    0.92
     Hussein
    0.86
     Ack
    0.85
     Obama
    0.84
     Freeze
    0.83
     Universe
    0.83
     Spock
    0.80
     Duterte
    0.78
     Joseph
    0.78
    Act Density 2.275%

    No Known Activations