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

    Neuronpedia

    INDEX
    Explanations

    references to sections or parts of the document where further information is provided

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.57
    oredCriteria
    -0.54
    heid
    -0.51
     g
    -0.50
     v
    -0.49
     Man
    -0.48
    TagHelper
    -0.48
     <>",
    -0.47
     just
    -0.47
    ghold
    -0.47
    POSITIVE LOGITS
     fubject
    0.80
    ](#
    0.74
     purpoſe
    0.72
     myſelf
    0.71
     poffible
    0.68
     fhort
    0.67
     occaf
    0.66
     Chriftian
    0.65
     uniqlo
    0.64
     itſelf
    0.64
    Act Density 1.251%

    No Known Activations