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

    Neuronpedia

    INDEX
    Explanations

    phrases related to establishing groundwork or foundations for concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uil
    -0.18
    oire
    -0.15
    oi
    -0.15
    lobe
    -0.15
    folio
    -0.15
    shal
    -0.15
    illet
    -0.14
     Bernardino
    -0.14
    iro
    -0.14
    isson
    -0.14
    POSITIVE LOGITS
     laid
    0.30
     groundwork
    0.28
     bare
    0.27
     lays
    0.25
     down
    0.24
     foundations
    0.22
     laying
    0.22
     foundation
    0.22
     claim
    0.22
     Bare
    0.21
    Act Density 0.014%

    No Known Activations