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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "was" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruc
    -0.16
    eria
    -0.15
    енз
    -0.14
    ofire
    -0.14
    astle
    -0.14
    åħ¥ãĤĬ
    -0.14
     Sax
    -0.14
    woff
    -0.14
    repid
    -0.14
     prostitutas
    -0.14
    POSITIVE LOGITS
     alone
    0.23
     accompanied
    0.21
     seen
    0.19
     wearing
    0.19
     familiar
    0.18
    alone
    0.18
     unarmed
    0.17
     bare
    0.17
     taken
    0.17
     staying
    0.16
    Act Density 0.053%

    No Known Activations