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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating disputes or conflicts among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.75
     TextInputType
    -0.55
     Raza
    -0.54
     السعود
    -0.54
     eventdata
    -0.53
    Raycast
    -0.52
     Alamos
    -0.51
     Adamson
    -0.50
    EndInit
    -0.50
    PerformLayout
    -0.50
    POSITIVE LOGITS
     Roman
    1.04
     Rome
    1.01
     Romans
    0.95
    Roman
    0.94
     Caesar
    0.92
    Rome
    0.90
     Pompey
    0.80
     römischen
    0.80
     Hadrian
    0.79
     Augustus
    0.78
    Act Density 0.255%

    No Known Activations