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

    Neuronpedia

    INDEX
    Explanations

    instances of objects or entities being overturned or toppled

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uro
    -0.07
    aira
    -0.07
    égor
    -0.07
    leaders
    -0.06
    iar
    -0.06
    jis
    -0.06
     Bless
    -0.06
    warm
    -0.06
     Marl
    -0.06
    icio
    -0.06
    POSITIVE LOGITS
    NDER
    0.07
    .GetInstance
    0.07
     mỹ
    0.06
     celib
    0.06
    FORMAT
    0.06
    assa
    0.06
     Wein
    0.06
     lẽ
    0.06
     DISP
    0.06
    hte
    0.06
    Act Density 0.013%

    No Known Activations