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

    Neuronpedia

    INDEX
    Explanations

    references to deleted or archived content in a database context

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

    deleted or removed status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.75
     CURIAM
    -0.65
    hyrchwyd
    -0.62
     EconPapers
    -0.56
    bootstrapcdn
    -0.55
    InitVars
    -0.54
    Priorities
    -0.54
    LookAnd
    -0.54
    BeginContext
    -0.53
    MessageTagHelper
    -0.53
    POSITIVE LOGITS
    isDeleted
    0.61
     deleted
    0.61
     Deleted
    0.56
    IsDeleted
    0.53
     trash
    0.53
    Deleted
    0.52
    deleted
    0.51
     Trash
    0.50
     restoration
    0.49
     garbage
    0.49
    Act Density 0.007%

    No Known Activations