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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nock
    -0.16
    amba
    -0.15
    wner
    -0.15
    dge
    -0.15
    igner
    -0.15
    disposing
    -0.15
    ngrx
    -0.15
    maries
    -0.15
    .isAuthenticated
    -0.14
    icari
    -0.14
    POSITIVE LOGITS
     trying
    0.17
     doing
    0.16
    ood
    0.15
    à¥Ģà¤ĸ
    0.15
    mit
    0.15
    bens
    0.15
    βολ
    0.14
    714
    0.14
     looking
    0.14
    136
    0.13
    Act Density 0.323%

    No Known Activations