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

    Neuronpedia

    INDEX
    Explanations

    phrases related to warranties and purposes of software usage

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

    fitness for a particular purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tazama
    -0.40
     magic
    -0.38
    protoimpl
    -0.37
    oneofs
    -0.37
     sim
    -0.36
     mim
    -0.34
     repa
    -0.34
     ProtoMessage
    -0.33
    dcmtk
    -0.33
    AfterEach
    -0.32
    POSITIVE LOGITS
     PURPOSE
    1.11
    PURPOSE
    0.89
     purposes
    0.83
     Purposes
    0.80
     Purpose
    0.79
    purposes
    0.79
    Purpose
    0.77
     purpose
    0.75
    purpose
    0.73
     purpoſe
    0.70
    Act Density 0.010%

    No Known Activations