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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to the concept of value or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.65
    èdia
    -0.64
    UnusedPrivate
    -0.60
     Paglinawan
    -0.55
    pinos
    -0.53
    __))
    -0.53
    tijds
    -0.52
     voici
    -0.51
    spyOn
    -0.51
    AntiForgeryToken
    -0.51
    POSITIVE LOGITS
     matters
    2.85
     matter
    2.84
     mattered
    2.50
    matters
    2.49
    matter
    2.45
     Matter
    2.33
     Matters
    2.30
     MATTER
    2.29
     MATTERS
    2.27
    Matter
    2.23
    Act Density 0.367%

    No Known Activations