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

    Neuronpedia

    INDEX
    Explanations

    references to authority and its various aspects or implications within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gâ
    -0.67
    pening
    -0.63
    NECTIONS
    -0.60
     Rens
    -0.60
    icula
    -0.60
     recession
    -0.59
    parcel
    -0.59
     Wad
    -0.59
    Transferred
    -0.59
     Wes
    -0.58
    POSITIVE LOGITS
     Authority
    2.49
     authority
    2.40
     AUTHORITY
    2.38
    authority
    2.35
    Authority
    2.33
     authorities
    2.05
     Authorities
    2.00
    authorities
    1.89
     autorité
    1.83
     autoridad
    1.75
    Act Density 0.109%

    No Known Activations