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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of usage and utilization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     usual
    -0.22
    raz
    -0.20
     useful
    -0.20
    ships
    -0.19
     usefulness
    -0.18
    ship
    -0.16
     Useful
    -0.16
    eced
    -0.15
    rim
    -0.15
    thon
    -0.15
    POSITIVE LOGITS
    fully
    0.40
    age
    0.31
    ful
    0.30
    full
    0.29
    FUL
    0.29
    fulness
    0.29
    lessly
    0.27
    able
    0.23
    æĪ¶
    0.19
    FULL
    0.18
    Act Density 0.128%

    No Known Activations