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

    Neuronpedia

    INDEX
    Explanations

    terms related to ownership and belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.63
     χρό
    -0.62
    etah
    -0.61
    agreb
    -0.60
    AntiForgeryToken
    -0.57
     Torah
    -0.55
     yeterli
    -0.55
     Saif
    -0.55
     Lehigh
    -0.54
    crose
    -0.54
    POSITIVE LOGITS
     belong
    1.64
     belongs
    1.62
    belong
    1.52
     Belong
    1.51
    belongs
    1.48
     belonging
    1.44
     belonged
    1.40
    belongsTo
    1.22
     apparten
    1.10
     pertenece
    1.09
    Act Density 0.106%

    No Known Activations