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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oprot
    -0.66
     становника
    -0.60
    harusnya
    -0.55
     chofe
    -0.54
    addPreferredGap
    -0.52
     uſe
    -0.52
    Probably
    -0.51
     uſed
    -0.51
    żeli
    -0.50
     bothered
    -0.49
    POSITIVE LOGITS
     glorious
    0.77
    ]!
    0.60
    っております
    0.59
     thee
    0.58
    !”
    0.57
    でございます
    0.57
    !")
    0.57
    UUUU
    0.56
     thy
    0.56
    EEEEEE
    0.55
    Act Density 0.374%

    No Known Activations