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

    Neuronpedia

    INDEX
    Explanations

    phrases related to systemic inequality and social support systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     implication
    -0.14
     THEN
    -0.14
    engo
    -0.13
     каз
    -0.13
     Stability
    -0.13
    á»Ļt
    -0.13
    izens
    -0.13
     æ¤
    -0.13
    oui
    -0.13
     Hyde
    -0.13
    POSITIVE LOGITS
    ythe
    0.18
    umas
    0.17
    623
    0.16
    canf
    0.15
    ushman
    0.14
    /Dk
    0.14
    924
    0.14
    οκ
    0.14
    Ymd
    0.14
    etas
    0.14
    Act Density 0.147%

    No Known Activations