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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating official statements or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sey
    -0.21
    -scalable
    -0.18
    ongan
    -0.18
    usu
    -0.16
    acha
    -0.15
    ìĦł
    -0.15
    xing
    -0.14
     nhau
    -0.14
     Glo
    -0.14
    Ñģлов
    -0.14
    POSITIVE LOGITS
    edly
    0.18
    ellite
    0.18
    andalone
    0.17
    naire
    0.17
    naires
    0.16
    holders
    0.16
    ihn
    0.16
    cipher
    0.16
    strup
    0.15
    hips
    0.15
    Act Density 0.028%

    No Known Activations