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

    Neuronpedia

    INDEX
    Explanations

    keywords relating to factual information and belief statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reef
    -0.65
     Weston
    -0.64
     KS
    -0.59
     Watkins
    -0.57
     Allied
    -0.56
     Kau
    -0.55
     reprinted
    -0.54
     Fernandez
    -0.54
     Flore
    -0.53
     Cath
    -0.52
    POSITIVE LOGITS
    usterity
    1.01
    theless
    0.99
    \)
    0.96
    estine
    0.95
    '?
    0.93
    »
    0.93
    É
    0.88
    %"
    0.88
    terday
    0.87
    /,
    0.86
    Act Density 0.454%

    No Known Activations