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

    Neuronpedia

    INDEX
    Explanations

    terms related to weight and heaviness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rese
    -0.15
    ihn
    -0.14
     Det
    -0.14
    lu
    -0.14
    sez
    -0.14
    uo
    -0.14
    azes
    -0.14
    eck
    -0.14
    angan
    -0.14
     Duplicate
    -0.13
    POSITIVE LOGITS
    -weight
    0.20
     weight
    0.17
    weight
    0.16
    isser
    0.15
    weights
    0.15
     weights
    0.15
    179
    0.14
     weigh
    0.14
    ayout
    0.14
    Weight
    0.14
    Act Density 0.062%

    No Known Activations