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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating similarity or reference to previous concepts or conditions

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

    same text contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.41
     PSA
    -0.40
     kapp
    -0.39
    Diweddarwch
    -0.39
     galle
    -0.38
     convin
    -0.38
    RemoteException
    -0.38
     disambigu
    -0.37
     shutterstock
    -0.36
    thansa
    -0.36
    POSITIVE LOGITS
     dieselben
    0.74
     dieselbe
    0.72
    zelfde
    0.70
     mesmos
    0.69
     same
    0.68
     mêmes
    0.67
    same
    0.66
    Same
    0.66
     aynı
    0.66
     mesma
    0.65
    Act Density 0.117%

    No Known Activations