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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Chaplin" or associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.48
     intensify
    -0.64
     mustered
    -0.62
     consolidate
    -0.59
    IEnumerator
    -0.59
     materialize
    -0.59
    chränk
    -0.58
    InvalidProtocol
    -0.58
     modernize
    -0.57
     renew
    -0.57
    POSITIVE LOGITS
     Cha
    1.52
    Cha
    1.42
     cha
    1.19
     Chá
    1.17
     CHA
    1.15
     effe
    1.09
     Chamb
    1.08
     Chap
    1.05
     Chaves
    1.05
     haer
    1.04
    Act Density 0.045%

    No Known Activations