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

    Neuronpedia

    INDEX
    Explanations

    terms related to historical and structural analysis in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ability
    -0.19
    ilians
    -0.17
    ency
    -0.16
    ilian
    -0.16
    eree
    -0.16
    ary
    -0.16
    iran
    -0.15
    erb
    -0.15
    LEV
    -0.15
    avid
    -0.15
    POSITIVE LOGITS
    ique
    0.26
    IQUE
    0.20
    ulaire
    0.20
    taire
    0.20
    aire
    0.19
    istique
    0.18
    naire
    0.17
    iques
    0.17
    rale
    0.17
    rique
    0.17
    Act Density 0.041%

    No Known Activations