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

    Neuronpedia

    INDEX
    Explanations

    references to weight and weight capacity of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¾
    -0.15
    fty
    -0.14
     Dup
    -0.14
     風
    -0.13
    umph
    -0.13
    rique
    -0.13
    edik
    -0.13
    andon
    -0.13
     Duplicate
    -0.13
    fields
    -0.13
    POSITIVE LOGITS
     weight
    0.27
    weight
    0.24
     weights
    0.23
    -weight
    0.23
    weights
    0.22
     WEIGHT
    0.21
     Weight
    0.21
    .weight
    0.21
    Weights
    0.20
    (weight
    0.20
    Act Density 0.091%

    No Known Activations