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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate relationships or actions involving people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.68
    ьаж
    -0.57
     jao
    -0.55
    كويكب
    -0.53
     Мексичка
    -0.52
     ngo
    -0.51
    EIP
    -0.51
    つも
    -0.48
    剤
    -0.47
    Geplaatst
    -0.47
    POSITIVE LOGITS
    ซึ่ง
    0.75
     which
    0.74
     who
    0.69
     shorthand
    0.69
     imageNamed
    0.65
     tromper
    0.64
     waarmee
    0.63
     devenus
    0.62
     mukana
    0.60
    formerly
    0.60
    Act Density 0.374%

    No Known Activations