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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reconstruction or restoring something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reconstruction processes or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cart
    -0.88
    cius
    -0.87
    ventus
    -0.79
    arez
    -0.78
    uana
    -0.77
    ammy
    -0.76
    uay
    -0.76
    die
    -0.75
    holders
    -0.75
    bags
    -0.75
    POSITIVE LOGITS
     reconstruction
    1.20
     reconstruct
    1.09
     reconstructed
    0.98
    ations
    0.79
    urally
    0.78
     Reconstruction
    0.76
     excav
    0.74
    ions
    0.74
     tempor
    0.73
     reprodu
    0.72
    Act Density 0.013%

    No Known Activations