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

    Neuronpedia

    INDEX
    Explanations

    terms associated with authority and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chiato
    -0.74
    lanzen
    -0.68
    tings
    -0.66
    ness
    -0.66
     createSlice
    -0.66
    ings
    -0.64
    ickle
    -0.63
     Aniston
    -0.62
     Rens
    -0.61
    amesh
    -0.61
    POSITIVE LOGITS
     Authority
    1.67
     authorities
    1.66
     authority
    1.62
    authority
    1.61
     AUTHORITY
    1.60
    Authority
    1.59
    authorities
    1.53
     Authorities
    1.53
    Authorities
    1.32
     autorité
    1.24
    Act Density 0.068%

    No Known Activations