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

    Neuronpedia

    INDEX
    Explanations

    words related to harvesting or obtaining something, such as reaping or reaping

    oai_token-act-pair · gpt-3.5-turbo

    words with suffixes related to modification or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mson
    -0.78
     substituted
    -0.66
    acca
    -0.64
     deported
    -0.62
     substit
    -0.61
     Bangalore
    -0.61
     Flint
    -0.60
     Gray
    -0.60
     Delete
    -0.59
    Chelsea
    -0.58
    POSITIVE LOGITS
    vern
    0.76
    prises
    0.71
    igion
    0.68
    kefeller
    0.68
    DOM
    0.68
    uin
    0.67
    phony
    0.66
    quit
    0.65
    aliation
    0.65
    arious
    0.64
    Act Density 0.088%

    No Known Activations