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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experience and identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -1.02
     Witt
    -0.81
    
    -0.78
     Assisi
    -0.76
    meng
    -0.75
     Omen
    -0.72
     Bub
    -0.71
     οποία
    -0.71
    ses
    -0.71
    ns
    -0.71
    POSITIVE LOGITS
     صوتيه
    0.92
     στη
    0.88
    waukee
    0.85
     Bue
    0.82
     Buxton
    0.81
     detainees
    0.81
     Parke
    0.80
     aDecoder
    0.80
    bilang
    0.80
     detenidos
    0.79
    Act Density 0.058%

    No Known Activations