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

    Neuronpedia

    INDEX
    Explanations

    phrases related to redundancy or excessiveness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to redundancy and continuity in processes or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Iv
    -0.88
    uana
    -0.83
    uay
    -0.80
    Beer
    -0.78
    WAY
    -0.78
    dp
    -0.75
    gress
    -0.75
    igers
    -0.74
    bern
    -0.74
    ress
    -0.73
    POSITIVE LOGITS
     redundancy
    1.12
     redund
    1.04
     redundant
    1.03
    nces
    0.81
    essential
    0.80
     interrupt
    0.79
     Mub
    0.76
     reliability
    0.76
     contingency
    0.76
     layers
    0.74
    Act Density 0.052%

    No Known Activations