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

    Neuronpedia

    INDEX
    Explanations

    articles and demonstrative pronouns in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.24
     متعلقه
    -1.20
     auffi
    -1.12
     Monfieur
    -1.11
     ſche
    -1.06
    Tikang
    -1.01
     iſt
    -1.00
     houſe
    -1.00
     purpoſe
    -0.99
     ―――――
    -0.98
    POSITIVE LOGITS
     a
    0.62
     
    0.61
    ,
    0.60
    …
    0.57
     "
    0.56
    .
    0.56
     “
    0.54
     in
    0.54
      
    0.54
    ...
    0.53
    Act Density 0.488%

    No Known Activations