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

    Neuronpedia

    INDEX
    Explanations

    qualifiers that describe the degree or extent of attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .appspot
    -0.15
    rowsable
    -0.15
    919
    -0.15
    .scalablytyped
    -0.15
    wright
    -0.15
     nackte
    -0.14
    ież
    -0.14
    ilis
    -0.14
    ity
    -0.14
    chner
    -0.13
    POSITIVE LOGITS
    uppies
    0.16
    upp
    0.16
    aches
    0.16
    üç
    0.14
    apos
    0.14
     Doch
    0.13
    uppy
    0.13
     scaler
    0.13
    λεκ
    0.13
    ications
    0.13
    Act Density 0.220%

    No Known Activations