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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the process of reconstructing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reconstruction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.96
    cart
    -0.88
    holders
    -0.80
    bara
    -0.76
    ventus
    -0.75
    die
    -0.74
    uana
    -0.74
    OPA
    -0.73
    nit
    -0.73
    Demand
    -0.72
    POSITIVE LOGITS
     reconstruction
    1.18
     reconstruct
    1.08
     reconstructed
    1.00
     Reconstruction
    0.81
     excav
    0.71
     rall
    0.71
     reprodu
    0.70
    urally
    0.70
     pse
    0.69
     recre
    0.69
    Act Density 0.016%

    No Known Activations