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

    Neuronpedia

    INDEX
    Explanations

    words related to conducting searches or investigations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "search" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ervatives
    -0.73
    oshenko
    -0.69
    olics
    -0.69
    çļ
    -0.69
    SourceFile
    -0.66
    ector
    -0.66
     Palest
    -0.66
    aft
    -0.65
     Presbyter
    -0.64
    icka
    -0.64
    POSITIVE LOGITS
     search
    3.81
     searches
    2.78
     Search
    2.66
    search
    2.48
     searched
    2.35
    Search
    2.31
     searching
    2.20
     sear
    1.90
     hunt
    1.70
     Sear
    1.63
    Act Density 0.011%

    No Known Activations