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

    Neuronpedia

    INDEX
    Explanations

    locations or settings within a narrative

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ican
    -0.73
     Canad
    -0.72
    ership
    -0.71
     Stability
    -0.67
    icans
    -0.67
     VIDEOS
    -0.66
    FK
    -0.65
    ernel
    -0.62
    ebin
    -0.62
    oret
    -0.61
    POSITIVE LOGITS
     irresist
    0.91
     toward
    0.88
     towards
    0.88
    entious
    0.86
     aback
    0.85
     into
    0.84
     drawn
    0.84
     thereto
    0.81
     Drawn
    0.75
     Into
    0.73
    Act Density 0.027%

    No Known Activations