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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collaboration and collective effort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.36
    氏は
    -0.34
     itself
    -0.33
     its
    -0.32
     خودش
    -0.32
     cilvē
    -0.31
     Δ
    -0.31
     is
    -0.30
     sitesinde
    -0.29
     commentary
    -0.28
    POSITIVE LOGITS
     ourselves
    1.51
     our
    1.10
    我们的
    0.92
    我們的
    0.91
    Our
    0.91
     nossa
    0.91
     jesteśmy
    0.88
     наших
    0.87
    aliśmy
    0.86
     nossas
    0.85
    Act Density 1.804%

    No Known Activations