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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives and descriptors that convey quality and effectiveness

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

    truly, true

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.54
    InitVars
    -0.52
     Majefty
    -0.49
     leaſt
    -0.48
     Reſ
    -0.47
    CodedInputStream
    -0.46
    ſelf
    -0.45
     normale
    -0.44
     Anſ
    -0.43
     Chriftian
    -0.43
    POSITIVE LOGITS
     truly
    1.28
    truly
    1.23
     Truly
    1.07
    Truly
    1.07
     verdaderamente
    1.03
     veramente
    0.82
     verdadera
    0.81
     realmente
    0.80
     true
    0.80
     véritable
    0.80
    Act Density 0.028%

    No Known Activations