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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geſch
    -1.62
    <unused43>
    -1.57
    <unused74>
    -1.56
    <unused23>
    -1.56
    <unused41>
    -1.56
    <unused79>
    -1.55
    <unused80>
    -1.55
    <unused42>
    -1.55
    [@BOS@]
    -1.55
    <unused3>
    -1.55
    POSITIVE LOGITS
     is
    2.88
     was
    1.79
     has
    1.54
     are
    1.48
     will
    1.30
     
    1.23
     can
    1.22
     of
    1.20
     in
    1.15
    ↵
    1.10
    Act Density 0.937%

    No Known Activations