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

    Neuronpedia

    INDEX
    Explanations

    terms related to removing or deleting items

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

    "Removed" or "removing" followed by "from"

    np_acts-logits-general · gemini-2.0-flash

    remove something fromlists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onPostExecute
    -0.60
    UnknownFields
    -0.53
    Personensuche
    -0.53
    StoryboardSegue
    -0.52
    textTheme
    -0.51
    LookAnd
    -0.51
    complexContent
    -0.50
     <<=
    -0.49
    splitting
    -0.49
     GlobalKey
    -0.49
    POSITIVE LOGITS
     khỏi
    1.40
     from
    1.38
    from
    1.06
     therefrom
    1.00
     FROM
    0.97
     dari
    0.96
     från
    0.91
     removes
    0.91
     removed
    0.89
    ออก
    0.89
    Act Density 0.380%

    No Known Activations