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

    Neuronpedia

    INDEX
    Explanations

    instances of physical or emotional removal or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Christopher eight years later

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.47
    DeleteBehavior
    -0.47
     فريبيس
    -0.46
    toires
    -0.45
    ItemBackground
    -0.44
     Вікіпе
    -0.44
    yskland
    -0.43
     aDecoder
    -0.42
    Diwedd
    -0.42
     rhestr
    -0.40
    POSITIVE LOGITS
     preferring
    0.40
     preferred
    0.40
     later
    0.40
     soon
    0.39
     altogether
    0.37
     Later
    0.37
    ogos
    0.36
    テンツ
    0.35
     suspending
    0.34
    ientôt
    0.34
    Act Density 0.148%

    No Known Activations