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

    Neuronpedia

    INDEX
    Explanations

    negative contexts related to ability and expectations in various scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.55
    None
    -0.53
     NSCoder
    -0.53
     None
    -0.50
    :✨
    -0.50
     NONE
    -0.50
     Autorisations
    -0.49
     rien
    -0.47
    Nothing
    -0.46
     ویکی‌آمباردا
    -0.46
    POSITIVE LOGITS
     anymore
    2.58
     enää
    1.45
     längre
    1.32
     lenger
    1.28
     artık
    1.21
     longer
    1.20
     længere
    1.18
     دیگر
    1.13
     nữa
    1.09
    不再
    1.05
    Act Density 0.387%

    No Known Activations