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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of completion or tasks being completed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    completion and subsequent actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     userSchema
    -0.53
    arache
    -0.50
    <bos>
    -0.49
     UserDao
    -0.49
     galinha
    -0.48
    ssize
    -0.47
    Wire
    -0.47
     Zwer
    -0.47
     Brag
    -0.47
     User
    -0.46
    POSITIVE LOGITS
     Completion
    0.85
    completion
    0.82
     completion
    0.78
    Completion
    0.70
     comple
    0.64
    GIVEREF
    0.60
     completeness
    0.60
     Comple
    0.58
    ็จ
    0.57
    comple
    0.56
    Act Density 0.009%

    No Known Activations