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

    Neuronpedia

    INDEX
    Explanations

    references to groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (es
    -0.22
    ï¸ı
    -0.18
    ìľ¨
    -0.16
    ayne
    -0.15
    ship
    -0.15
    berg
    -0.15
    lock
    -0.15
    wner
    -0.14
    asio
    -0.14
     Insecta
    -0.14
    POSITIVE LOGITS
     who
    0.38
     whom
    0.29
    who
    0.28
    /entities
    0.27
    /groups
    0.24
     whose
    0.23
     Who
    0.23
     اÙĦØ°ÙĬÙĨ
    0.22
    Who
    0.21
    è°ģ
    0.19
    Act Density 0.116%

    No Known Activations