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

    Neuronpedia

    INDEX
    Explanations

    locations, specifically places called "Mountain" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Mountain."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ional
    -0.96
    lest
    -0.87
    ifice
    -0.84
    orate
    -0.81
    metic
    -0.80
    isen
    -0.79
    alien
    -0.78
    soc
    -0.75
    ivity
    -0.75
    ded
    -0.75
    POSITIVE LOGITS
     Mountain
    1.12
     Riders
    0.95
     Island
    0.88
     biking
    0.87
     Bike
    0.86
     Highway
    0.84
     Valley
    0.83
     Alto
    0.82
     Mountains
    0.81
     Meadows
    0.79
    Act Density 0.007%

    No Known Activations