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

    Neuronpedia

    INDEX
    Explanations

    names and identifiers relating to entities and acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns and named entities, particularly surnames and brand names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     IConfiguration
    -0.48
     inten
    -0.42
    TargetException
    -0.41
     ston
    -0.38
    \!
    -0.38
    Wahl
    -0.37
     intens
    -0.36
     conto
    -0.36
     inappro
    -0.36
     Stich
    -0.36
    POSITIVE LOGITS
     Ae
    0.63
     ModelExpression
    0.61
    Ae
    0.60
     ciasc
    0.55
     ProtoMessage
    0.55
     ciascuno
    0.53
    Aer
    0.52
    AE
    0.51
    脚注の使い方
    0.51
     Aer
    0.50
    Act Density 0.253%

    No Known Activations