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

    Neuronpedia

    INDEX
    Explanations

    the presence of capitalization in tokens, particularly referring to specific entities or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.16
    infeld
    -0.16
     jenter
    -0.16
    ersions
    -0.16
    angler
    -0.15
    emann
    -0.15
    NSIndexPath
    -0.14
    PackageName
    -0.14
    γκÏĮ
    -0.14
     nebu
    -0.14
    POSITIVE LOGITS
    amel
    0.17
    cha
    0.16
    æĢĢ
    0.16
     Reno
    0.15
    river
    0.14
     Crawford
    0.14
    am
    0.14
    ag
    0.13
    essler
    0.13
    mediate
    0.13
    Act Density 0.071%

    No Known Activations