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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics or figures related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erer
    -0.75
    estine
    -0.74
    timer
    -0.71
    rium
    -0.70
    ulates
    -0.68
    money
    -0.68
    izoph
    -0.65
    lied
    -0.64
    inges
    -0.64
    evin
    -0.64
    POSITIVE LOGITS
    lbs
    1.08
     pounds
    1.04
     lbs
    1.02
     miles
    0.97
     kilometers
    0.92
     consecutive
    0.90
     kilograms
    0.90
     calories
    0.89
    bp
    0.88
     feet
    0.87
    Act Density 0.146%

    No Known Activations