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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    845
    -0.17
    being
    -0.17
     being
    -0.16
    oya
    -0.16
    entin
    -0.16
    yny
    -0.15
    Being
    -0.15
    -being
    -0.14
    122
    -0.14
     NavParams
    -0.14
    POSITIVE LOGITS
    ildo
    0.15
    enance
    0.15
    éīĦ
    0.14
    'gc
    0.14
    velope
    0.14
    friend
    0.14
     liken
    0.14
    organisation
    0.14
    iali
    0.14
    adia
    0.14
    Act Density 0.111%

    No Known Activations