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

    Neuronpedia

    INDEX
    Explanations

    phrases related to efficiency and reductions in cost or resource usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meis
    -0.19
    kening
    -0.16
    åī£
    -0.15
    åŁ
    -0.14
    ARGIN
    -0.14
    ç«
    -0.14
    ledo
    -0.14
    oken
    -0.14
     oppon
    -0.14
    aphore
    -0.14
    POSITIVE LOGITS
     ent
    0.17
     exc
    0.15
    æ´ª
    0.15
    bern
    0.15
     invalid
    0.15
    DEN
    0.15
    eld
    0.14
    orian
    0.14
    evil
    0.14
    cej
    0.14
    Act Density 0.335%

    No Known Activations