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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "use" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¦Ĥä½ķ
    -0.16
    aurus
    -0.15
    inger
    -0.15
    onto
    -0.15
    User
    -0.15
    _users
    -0.14
    opal
    -0.14
    imed
    -0.14
    /full
    -0.14
    ufen
    -0.14
    POSITIVE LOGITS
    fully
    0.34
    lessly
    0.29
    ful
    0.24
    FUL
    0.24
     techniques
    0.23
    fulness
    0.21
     caution
    0.21
    full
    0.21
     only
    0.21
     discretion
    0.20
    Act Density 0.171%

    No Known Activations