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

    Neuronpedia

    INDEX
    Explanations

    phrases related to overuse or excessive behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reve
    -0.18
    gle
    -0.17
    aub
    -0.16
    leton
    -0.16
    gebn
    -0.15
    öl
    -0.15
    _dispatch
    -0.14
    tri
    -0.14
    ropol
    -0.14
     Rosenberg
    -0.14
    POSITIVE LOGITS
     counter
    0.31
    -counter
    0.30
     Counter
    0.28
    counter
    0.28
    Counter
    0.26
    ounter
    0.22
    _counter
    0.21
    (counter
    0.21
    OUNTER
    0.20
    ternet
    0.20
    Act Density 0.009%

    No Known Activations