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

    Neuronpedia

    INDEX
    Explanations

    words related to procedures or actions, particularly those starting with "pe"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "pe."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.89
    schild
    -0.72
     Kirin
    -0.69
    enegger
    -0.67
     GOODMAN
    -0.66
     swirling
    -0.64
     shutter
    -0.63
    ãĤ¨ãĥ«
    -0.62
    ãĥĦ
    -0.61
     guiActiveUnfocused
    -0.61
    POSITIVE LOGITS
    pe
    1.08
    cific
    1.02
    asant
    0.97
    rer
    0.96
    oples
    0.96
    aks
    0.93
    eps
    0.93
    lement
    0.91
    anut
    0.91
    cial
    0.90
    Act Density 0.008%

    No Known Activations