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

    Neuronpedia

    INDEX
    Explanations

    terms related to increments and drag in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    runOnUiThread
    -0.50
    OGND
    -0.48
    exitRule
    -0.44
    Personensuche
    -0.42
    AccessorTable
    -0.40
     Encuentra
    -0.40
    RepeatedField
    -0.40
     Herausgeber
    -0.39
     connaissent
    -0.39
     OFDb
    -0.39
    POSITIVE LOGITS
     incremental
    0.87
     increment
    0.87
     Increment
    0.79
     Incremental
    0.77
    Incremental
    0.73
    Increment
    0.66
    increment
    0.65
     Drag
    0.59
    Drag
    0.57
    Dragon
    0.57
    Act Density 0.305%

    No Known Activations