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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or transfer from one entity to another

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooks
    -0.73
    folk
    -0.72
    cream
    -0.71
    ãĥ©ãĥ³
    -0.68
    lov
    -0.64
    hips
    -0.64
    len
    -0.62
    inders
    -0.61
    acements
    -0.61
    late
    -0.60
    POSITIVE LOGITS
     hundred
    1.07
     Hundred
    1.00
     dimensional
    0.96
     thousand
    0.92
     particular
    0.89
     Thousand
    0.87
     million
    0.84
     sided
    0.81
     lakh
    0.78
     minute
    0.75
    Act Density 0.108%

    No Known Activations