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

    Neuronpedia

    INDEX
    Explanations

    locations or events where people are instructed or invited to visit or stop by

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "stop by" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    attribute
    -0.77
     forgiven
    -0.71
    ãĤ¦ãĤ¹
    -0.69
     Fib
    -0.68
    lda
    -0.68
    uyomi
    -0.67
    esson
    -0.67
    aceutical
    -0.66
    deal
    -0.65
    agi
    -0.63
    POSITIVE LOGITS
     Locations
    0.99
     Tues
    0.94
     locations
    0.93
     booths
    0.92
    site
    0.91
     downtown
    0.90
     encamp
    0.90
     downstairs
    0.87
     weekends
    0.87
     tents
    0.86
    Act Density 0.833%

    No Known Activations