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

    Neuronpedia

    INDEX
    Explanations

    specific types of nouns and their relations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alin
    -0.18
    âĢĮدÙĩ
    -0.15
    .datatables
    -0.15
    æ³°
    -0.15
     Jackson
    -0.15
    íħIJ
    -0.15
     Sherman
    -0.15
    akis
    -0.14
    cente
    -0.14
    icros
    -0.14
    POSITIVE LOGITS
     Sam
    0.18
     SA
    0.17
     SAM
    0.17
     Samuel
    0.17
     sam
    0.16
     sa
    0.16
     Σα
    0.15
     SAC
    0.15
    Sam
    0.15
     islands
    0.15
    Act Density 0.046%

    No Known Activations