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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "edit" and related terms associated with editing and modifications

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

    editing text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.63
    __':
    -0.58
    getStringExtra
    -0.51
     Drapeau
    -0.51
    migrationBuilder
    -0.48
    getTest
    -0.47
    createServer
    -0.47
    DoubleQuotes
    -0.47
    RunWith
    -0.44
    __':
    -0.43
    POSITIVE LOGITS
     editing
    0.75
     edit
    0.74
     Editing
    0.72
     edited
    0.71
     edits
    0.70
     modif
    0.65
    Edited
    0.64
    Editing
    0.64
    edited
    0.64
    editing
    0.64
    Act Density 0.029%

    No Known Activations