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
     more
    -0.16
    δÏĮν
    -0.15
    inth
    -0.15
    ams
    -0.14
    bourg
    -0.14
     более
    -0.14
    burg
    -0.14
    scope
    -0.14
    pery
    -0.14
    olik
    -0.14
    POSITIVE LOGITS
    acci
    0.27
    ly
    0.26
     importantly
    0.26
    arda
    0.24
    afa
    0.23
    /all
    0.22
     likely
    0.21
     definitely
    0.21
    ecká
    0.20
     certainly
    0.19
    Act Density 0.032%

    No Known Activations