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

    Neuronpedia

    INDEX
    Explanations

    comparisons involving quantities or degrees

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that suggest a contrast or duality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emn
    -0.51
    iatus
    -0.49
    enger
    -0.49
     Peak
    -0.48
    ²¾
    -0.46
     Pixie
    -0.46
    ety
    -0.45
    earch
    -0.44
    aba
    -0.44
    tains
    -0.44
    POSITIVE LOGITS
    etheless
    0.62
     apologies
    0.56
     WARN
    0.52
    fortunately
    0.49
     preferably
    0.49
    entimes
    0.48
    markets
    0.46
     preferring
    0.45
     economists
    0.45
     congr
    0.45
    Act Density 1.923%

    No Known Activations