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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate an intention or purpose related to processes and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.58
    Pele
    -0.54
     Republi
    -0.51
    Incluso
    -0.50
     Pele
    -0.50
    sectional
    -0.49
    KeySpec
    -0.49
    CreateModel
    -0.48
    AccessorTable
    -0.48
    Demografie
    -0.48
    POSITIVE LOGITS
    MLLoader
    0.86
    PMailer
    0.76
    istoitu
    0.72
     fallait
    0.72
     soll
    0.71
     devaient
    0.71
    archiviato
    0.70
     devait
    0.70
     fallu
    0.70
     shall
    0.67
    Act Density 0.097%

    No Known Activations