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

    Neuronpedia

    INDEX
    Explanations

    terms associated with adding and increments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wikispecies
    -0.79
    maketitle
    -0.76
    Bibliografia
    -0.75
    thansa
    -0.73
    iconque
    -0.72
    findpost
    -0.72
    SourceChecksum
    -0.71
    archiviato
    -0.70
     Bourgeois
    -0.69
    НИК
    -0.68
    POSITIVE LOGITS
     added
    2.37
     adds
    2.25
     add
    2.20
     Adds
    2.19
     Added
    2.12
     adding
    2.12
    Added
    2.10
     Add
    2.10
    added
    2.09
     ADDED
    2.08
    Act Density 0.131%

    No Known Activations