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

    Neuronpedia

    INDEX
    Explanations

    references to fencing or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     préfé
    -0.78
    olesale
    -0.77
     bisous
    -0.76
    rétaire
    -0.73
     cornu
    -0.72
    erequisites
    -0.71
     constellations
    -0.70
    iosync
    -0.70
     ministre
    -0.69
    ynthetic
    -0.69
    POSITIVE LOGITS
     fence
    1.69
     fences
    1.50
     Fence
    1.37
    fence
    1.36
     fencing
    1.34
     fenced
    1.23
    上
    1.15
    Fence
    1.14
     Fencing
    1.09
    fenced
    0.94
    Act Density 0.066%

    No Known Activations