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

    Neuronpedia

    INDEX
    Explanations

    phrases related to undeniable proof or evidence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hunting
    -0.72
     funer
    -0.67
     Housing
    -0.62
     Solitaire
    -0.62
     quarters
    -0.61
     Franch
    -0.60
     redes
    -0.60
     dust
    -0.60
    nets
    -0.60
     straw
    -0.60
    POSITIVE LOGITS
    putable
    1.20
    akable
    1.11
    ably
    1.05
    cipline
    0.99
    arkable
    0.98
    uously
    0.98
    cipl
    0.98
    ensible
    0.96
    puted
    0.96
    uably
    0.94
    Act Density 0.027%

    No Known Activations