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

    Neuronpedia

    INDEX
    Explanations

    names of locations and historical facts, possibly related to the Ottoman Empire

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Heads
    -0.63
     tentacles
    -0.62
    heads
    -0.61
     kernels
    -0.58
     beats
    -0.58
    é¾įå¥ij士
    -0.57
     entitled
    -0.57
     corridors
    -0.57
     strengths
    -0.56
     almonds
    -0.56
    POSITIVE LOGITS
    ivil
    0.91
    vez
    0.91
    ternity
    0.83
     Klux
    0.80
    ctor
    0.79
    llor
    0.78
    zbek
    0.78
    nom
    0.78
    nsic
    0.77
    nder
    0.77
    Act Density 0.042%

    No Known Activations