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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating obligations or necessities related to personal or community responsibility

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

    connective words that introduce explanations or purposes (particularly "so" and "that" in clauses expressing intent or consequence).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     fact
    -0.52
    EDEFAULT
    -0.52
    RegistryLite
    -0.50
    MigrationBuilder
    -0.50
    Tikang
    -0.47
    endix
    -0.47
     ModelRenderer
    -0.45
     nahilalakip
    -0.45
     Italijanski
    -0.44
    Witness
    -0.43
    POSITIVE LOGITS
    
    0.54
     hopefully
    0.50
     pueda
    0.43
     möglichst
    0.41
    hopefully
    0.41
    Oneof
    0.39
     puissent
    0.39
     zodat
    0.39
    MethodManager
    0.38
     dotyczące
    0.38
    Act Density 0.143%

    No Known Activations