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

    Neuronpedia

    INDEX
    Explanations

    terms related to propagation in a technical or scientific context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    zną
    -0.68
     Etr
    -0.67
    \
    -0.67
    تس
    -0.65
     Lus
    -0.63
    ing
    -0.62
     grise
    -0.62
     Shum
    -0.60
    sk
    -0.59
    less
    -0.59
    POSITIVE LOGITS
     propag
    1.39
     Propag
    1.26
     Propagation
    1.13
     propagate
    1.12
    propag
    1.10
     propagating
    1.10
     propa
    1.06
     propagation
    1.05
     propagated
    1.00
    Propag
    0.98
    Act Density 0.003%

    No Known Activations