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

    Neuronpedia

    INDEX
    Explanations

    words associated with flow and passage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.20
    ece
    -0.18
    eck
    -0.18
    eum
    -0.16
    eil
    -0.16
    ei
    -0.15
    elem
    -0.15
     wedge
    -0.15
    399
    -0.15
    eve
    -0.14
    POSITIVE LOGITS
    ework
    0.34
    ename
    0.34
    eness
    0.34
    eman
    0.32
    edef
    0.32
    eland
    0.32
    ewise
    0.32
    eway
    0.31
    ethe
    0.31
    ereg
    0.30
    Act Density 0.252%

    No Known Activations