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

    Neuronpedia

    INDEX
    Explanations

    references to completion in various contexts

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

    task completion handlers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     userSchema
    -0.51
    WithIOException
    -0.50
     vraie
    -0.50
     strto
    -0.47
    mstyle
    -0.47
    BagConstraints
    -0.46
     juridiques
    -0.46
     généraux
    -0.46
     financieras
    -0.46
     لينك
    -0.45
    POSITIVE LOGITS
     Completion
    2.11
     completion
    2.06
    completion
    1.84
    Completion
    1.84
     Completing
    1.01
     completing
    0.99
     COMPLE
    0.98
     comple
    0.95
    COMPLE
    0.94
    comple
    0.87
    Act Density 0.005%

    No Known Activations