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

    Neuronpedia

    INDEX
    Explanations

    terminology related to statistical methods and causal inference in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _patches
    -0.17
    hea
    -0.17
    patch
    -0.16
    arith
    -0.16
    Patch
    -0.16
     patches
    -0.16
    okit
    -0.15
    _patch
    -0.15
    fighter
    -0.15
    सर
    -0.15
    POSITIVE LOGITS
     causal
    0.30
     treatment
    0.28
     Treatment
    0.26
     counter
    0.24
     Instrument
    0.23
     caus
    0.22
     treatments
    0.22
     Collider
    0.22
    -ca
    0.22
     Pearl
    0.22
    Act Density 0.006%

    No Known Activations