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

    Neuronpedia

    INDEX
    Explanations

    indicators of societal and cultural expectations or pressures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apro
    -0.16
     Hab
    -0.16
     Vie
    -0.15
     Alias
    -0.14
    anka
    -0.14
    itsu
    -0.14
    226
    -0.14
    ë§Īëĭ¤
    -0.13
    itta
    -0.13
    alsa
    -0.13
    POSITIVE LOGITS
     status
    0.22
     ÑģÑĤаÑĤÑĥÑģ
    0.22
     stigma
    0.21
    -status
    0.21
     STATUS
    0.20
    status
    0.20
     prestige
    0.19
     statuses
    0.18
     prest
    0.18
     setStatus
    0.18
    Act Density 0.164%

    No Known Activations