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

    Neuronpedia

    INDEX
    Explanations

    references to authority and discretion in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aida
    -0.17
    Ư
    -0.17
    agar
    -0.15
    iar
    -0.15
    lick
    -0.14
     Femme
    -0.14
    ấu
    -0.14
    енко
    -0.13
    orz
    -0.13
     Uph
    -0.13
    POSITIVE LOGITS
     authority
    0.46
     powers
    0.45
     power
    0.43
    authority
    0.35
    powers
    0.32
    power
    0.32
     latitude
    0.29
     Authority
    0.29
     pouvoir
    0.28
     authorities
    0.28
    Act Density 0.135%

    No Known Activations