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

    Neuronpedia

    INDEX
    Explanations

    operations involving multiplication and division

    oai_token-act-pair · gpt-3.5-turbo

    mathematical operations and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oho
    -0.80
    vironment
    -0.80
    hov
    -0.77
    twitch
    -0.77
    smoking
    -0.74
     Spit
    -0.73
    ãģł
    -0.73
    soDeliveryDate
    -0.69
    walker
    -0.68
    fell
    -0.68
    POSITIVE LOGITS
     multiply
    0.90
     increment
    0.90
     multipl
    0.89
     additive
    0.88
     numer
    0.87
    onent
    0.87
    ithmetic
    0.87
    ulative
    0.85
     arithmetic
    0.84
     multiplication
    0.83
    Act Density 0.048%

    No Known Activations