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

    Neuronpedia

    INDEX
    Explanations

    references to "people" and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (es
    -0.19
    ï¸ı
    -0.18
    wner
    -0.17
    Ùij
    -0.16
    engin
    -0.15
     οÏĢοίο
    -0.15
    stadt
    -0.15
    czy
    -0.14
    Äįel
    -0.14
    ptime
    -0.14
    POSITIVE LOGITS
     who
    0.47
     whom
    0.37
    who
    0.34
    /entities
    0.31
    's
    0.31
    /groups
    0.31
     whose
    0.29
     Who
    0.27
     اÙĦØ°ÙĬÙĨ
    0.27
    ’s
    0.25
    Act Density 0.111%

    No Known Activations