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

    Neuronpedia

    INDEX
    Explanations

    phrases related to saving and storing information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tanleria
    -0.69
    aclk
    -0.62
    chle
    -0.61
     Dyck
    -0.61
    ulur
    -0.60
    Географиясе
    -0.58
     Dyke
    -0.57
    protos
    -0.57
     Brito
    -0.57
    Же
    -0.56
    POSITIVE LOGITS
     Save
    1.57
     SAVE
    1.53
     saved
    1.52
     saves
    1.49
    Save
    1.49
     SAV
    1.48
     Saves
    1.46
     saving
    1.46
     save
    1.46
    SAV
    1.46
    Act Density 0.045%

    No Known Activations