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

    Neuronpedia

    INDEX
    Explanations

    references to social dynamics and group relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alone
    -0.23
    ãģłãģij
    -0.21
     themselves
    -0.20
     often
    -0.19
     sometimes
    -0.18
     altogether
    -0.18
     Alone
    -0.17
    à¹Ģà¸Ńà¸ĩ
    -0.17
     each
    -0.16
     only
    -0.16
    POSITIVE LOGITS
     except
    0.36
    except
    0.36
     кÑĢоме
    0.30
     imaginable
    0.30
    Except
    0.30
     Except
    0.30
    _except
    0.28
    including
    0.27
     vÄįetnÄĽ
    0.26
     INCLUDING
    0.25
    Act Density 0.451%

    No Known Activations