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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     that
    -0.47
     It
    -0.39
     other
    -0.35
     it
    -0.35
     song
    -0.32
     for
    -0.32
     we
    -0.31
    îtra
    -0.31
     its
    -0.29
     result
    -0.29
    POSITIVE LOGITS
     myſelf
    0.95
    <unused43>
    0.83
    <unused41>
    0.83
    ंदीखरीदारी
    0.83
    <unused17>
    0.82
    <pad>
    0.82
    <unused80>
    0.82
     メンテナ
    0.82
    MessageTagHelper
    0.82
    [@BOS@]
    0.82
    Act Density 0.605%

    No Known Activations