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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "remove" and its variants related to actions involving removal or deletion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    	Copyright
    -0.17
    ebra
    -0.16
    errat
    -0.16
    724
    -0.15
    Ñģол
    -0.15
     directions
    -0.14
    esty
    -0.13
     Eag
    -0.13
     royal
    -0.13
     Levine
    -0.13
    POSITIVE LOGITS
    akens
    0.22
    opoulos
    0.17
    amage
    0.15
    ated
    0.14
    ivatel
    0.14
    .tie
    0.13
     TMPro
    0.13
    rama
    0.13
    .dataTables
    0.13
    .Entities
    0.13
    Act Density 0.061%

    No Known Activations