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

    Neuronpedia

    INDEX
    Explanations

    the word "most" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mappedBy
    -0.16
    δÏĮν
    -0.16
    inand
    -0.15
    agus
    -0.15
    atori
    -0.15
     quite
    -0.15
     somewhat
    -0.15
     most
    -0.14
    aign
    -0.14
    rick
    -0.14
    POSITIVE LOGITS
     definitely
    0.24
     certainly
    0.23
     likely
    0.22
    arda
    0.21
    acci
    0.21
     Definitely
    0.21
    likely
    0.21
    ly
    0.20
     assured
    0.20
    afa
    0.20
    Act Density 0.033%

    No Known Activations