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

    Neuronpedia

    INDEX
    Explanations

    commands, particularly focused on the action of adding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bibliografia
    -0.79
    uxxxx
    -0.75
    Louie
    -0.75
    geist
    -0.71
     Wikispecies
    -0.71
    Jeb
    -0.71
     glyphicon
    -0.70
     Bourgeois
    -0.70
    НИК
    -0.70
    '],$
    -0.70
    POSITIVE LOGITS
    Add
    1.45
     Add
    1.45
     Adds
    1.44
     ADD
    1.43
    ADD
    1.38
     add
    1.35
     adds
    1.33
    add
    1.24
     Adder
    1.23
     adder
    1.20
    Act Density 0.108%

    No Known Activations