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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "update" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.59
    iverr
    -0.58
    DEFINE
    -0.53
    SneakyThrows
    -0.53
    圣节
    -0.52
    r
    -0.50
    MLLoader
    -0.50
     diser
    -0.50
    san
    -0.49
     Ca
    -0.49
    POSITIVE LOGITS
     updater
    1.05
     UPD
    0.98
    updateData
    0.97
    onUpdate
    0.96
     Updates
    0.94
    UpdateCommand
    0.89
     itſelf
    0.89
     EconPapers
    0.88
     updates
    0.88
     myſelf
    0.85
    Act Density 0.058%

    No Known Activations