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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "New."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NCY
    -0.15
    åħ
    -0.15
    ODO
    -0.15
    olated
    -0.15
    hattan
    -0.15
    .Core
    -0.14
    æĥħ
    -0.14
     MetroFramework
    -0.14
    ift
    -0.14
    uele
    -0.14
    POSITIVE LOGITS
     England
    0.18
     Braun
    0.18
     Britain
    0.18
     Haven
    0.17
     Mil
    0.17
     Era
    0.17
    England
    0.17
     Hope
    0.17
    leck
    0.16
    nan
    0.16
    Act Density 0.031%

    No Known Activations