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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to value and importance in various contexts

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

    Sentences referencing importance or relevance

    np_acts-logits-general · gemini-2.0-flash

    what matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    èdia
    -0.71
    AntiForgeryToken
    -0.56
    czej
    -0.52
    GTCX
    -0.51
    PONSE
    -0.51
     voici
    -0.51
    도록
    -0.50
    spyOn
    -0.49
     '__
    -0.48
     RSSSF
    -0.48
    POSITIVE LOGITS
     matters
    2.35
     matter
    2.33
     mattered
    2.07
    matters
    2.00
    matter
    1.98
     Matters
    1.93
     MATTER
    1.92
     Matter
    1.91
     MATTERS
    1.90
    Matters
    1.79
    Act Density 0.257%

    No Known Activations