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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity and social status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sez
    -0.19
     milieu
    -0.17
     plaint
    -0.16
     malign
    -0.15
     arcane
    -0.15
     :-)
    -0.15
     cach
    -0.14
     elapsed
    -0.14
     goodies
    -0.14
    BITS
    -0.14
    POSITIVE LOGITS
     ideologies
    0.18
     abol
    0.17
     ãĥ¼
    0.17
    aturated
    0.16
    -esque
    0.15
     rouge
    0.15
     downfall
    0.15
    Furthermore
    0.14
    ighb
    0.14
     statuses
    0.14
    Act Density 1.261%

    No Known Activations