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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, possibly associated with news or controversy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.76
    undai
    -0.56
    urtles
    -0.56
    lehem
    -0.55
    eatures
    -0.54
    ometimes
    -0.54
    oenix
    -0.54
    ģĸ
    -0.53
     streamed
    -0.53
     brill
    -0.51
    POSITIVE LOGITS
    's
    1.26
    ÃŃs
    0.80
     personally
    0.74
     himself
    0.73
     Syndrome
    0.71
    existent
    0.68
    ´
    0.67
    Care
    0.67
    tsy
    0.66
     Sr
    0.65
    Act Density 2.623%

    No Known Activations