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

    Neuronpedia

    INDEX
    Explanations

    statements or sentences expressing completions or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osaic
    -0.16
    strength
    -0.15
    bjerg
    -0.15
     Fortress
    -0.14
    rength
    -0.14
    æīįèĥ½
    -0.14
     Wing
    -0.14
     wing
    -0.14
    ist
    -0.13
    PRESSION
    -0.13
    POSITIVE LOGITS
    .SuspendLayout
    0.16
     Bran
    0.15
    лаÑĪ
    0.15
    Labels
    0.15
    enville
    0.15
     rebate
    0.14
    ierz
    0.14
    -fontawesome
    0.14
    :UITableView
    0.14
    xit
    0.13
    Act Density 0.296%

    No Known Activations