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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (es
    -0.21
    stadt
    -0.18
    ship
    -0.16
    berg
    -0.16
    ìľ¨
    -0.16
    ï¸ı
    -0.16
    asio
    -0.15
    ãģ¯ãģªãģĦ
    -0.15
    wner
    -0.14
    appName
    -0.14
    POSITIVE LOGITS
     who
    0.35
    /entities
    0.26
     whom
    0.26
    who
    0.25
    /groups
    0.24
     Who
    0.22
     whose
    0.21
     اÙĦØ°ÙĬÙĨ
    0.21
    hood
    0.19
    Who
    0.19
    Act Density 0.121%

    No Known Activations