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

    Neuronpedia

    INDEX
    Explanations

    locations specified in units of distance (e.g., km, miles)

    oai_token-act-pair · gpt-3.5-turbo

    geographical distances and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scrib
    -0.81
    ©¶æ
    -0.73
     Choice
    -0.67
     Scare
    -0.63
     Dying
    -0.63
     Toast
    -0.63
    Asset
    -0.62
    otten
    -0.62
     Baal
    -0.62
     Fake
    -0.61
    POSITIVE LOGITS
     kilometres
    1.04
     kilometers
    0.98
     distances
    0.97
     highways
    0.84
    outheast
    0.83
    km
    0.80
     km
    0.78
     inland
    0.76
     miles
    0.76
     northwest
    0.74
    Act Density 0.102%

    No Known Activations