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

    Neuronpedia

    INDEX
    Explanations

    adjectives referring to size or importance

    oai_token-act-pair · gpt-3.5-turbo

    the word "huge" and its variations, indicating emphasis on significance or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewed
    -0.88
    ices
    -0.85
    gemony
    -0.79
    istry
    -0.78
    manship
    -0.78
    utics
    -0.77
    former
    -0.74
    ople
    -0.71
    tein
    -0.70
    pai
    -0.69
    POSITIVE LOGITS
     amounts
    1.01
     chunk
    0.93
     amount
    0.90
     chunks
    0.90
     earthqu
    0.87
     disproportion
    0.87
     swath
    0.83
     leaps
    0.83
     difference
    0.83
     undertaking
    0.81
    Act Density 0.029%

    No Known Activations