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

    Neuronpedia

    INDEX
    Explanations

    references to authority and hierarchical structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    consin
    -0.74
    ifest
    -0.73
     योग
    -0.66
    ness
    -0.66
    INGS
    -0.63
    tings
    -0.63
     незавершена
    -0.62
    meral
    -0.61
    Sask
    -0.61
    hasNext
    -0.60
    POSITIVE LOGITS
    Authority
    1.26
    authority
    1.23
    authorities
    1.20
     authorities
    1.19
     AUTHORITY
    1.16
     authority
    1.16
     Authority
    1.14
     Authorities
    1.13
    GrantedAuthority
    1.02
     AUTHORITIES
    0.98
    Act Density 0.009%

    No Known Activations