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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "save" and related forms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tanleria
    -0.80
    tems
    -0.66
    Географиясе
    -0.63
     Brito
    -0.62
    SequentialGroup
    -0.61
    ORIENTATION
    -0.59
    FactoryBean
    -0.59
    aclk
    -0.58
     Dyke
    -0.58
    complexContent
    -0.57
    POSITIVE LOGITS
     Save
    2.08
     save
    2.03
     saving
    2.00
     saves
    1.99
     SAVE
    1.97
    Save
    1.95
     Saving
    1.93
     saved
    1.90
     Saves
    1.85
    save
    1.83
    Act Density 0.040%

    No Known Activations