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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations, specifically places like St. Petersburg and El Paso

    oai_token-act-pair · gpt-3.5-turbo

    references to specific cities, particularly St. Petersburg and El Paso

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    profit
    -0.71
    don
    -0.71
    know
    -0.71
    dy
    -0.70
    sense
    -0.68
    moving
    -0.62
    Trend
    -0.61
    ell
    -0.61
    PF
    -0.60
    verse
    -0.60
    POSITIVE LOGITS
     Petersburg
    1.00
    issance
    0.81
    sburg
    0.81
    ij士
    0.76
    ignt
    0.76
     Awakens
    0.75
     Springs
    0.74
     rall
    0.73
    burg
    0.72
    borg
    0.71
    Act Density 0.007%

    No Known Activations