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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or processes of adding and removing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nicio
    -0.55
    Lack
    -0.51
    inine
    -0.51
     brazos
    -0.50
    lack
    -0.47
     suspendu
    -0.47
     tsy
    -0.46
     creș
    -0.46
     للد
    -0.46
     semn
    -0.45
    POSITIVE LOGITS
    把
    1.36
    將
    1.30
     将
    1.29
    将
    1.29
     把
    1.25
    并将
    1.17
     將
    1.16
    要把
    1.13
    就把
    1.06
    我们将
    0.98
    Act Density 0.151%

    No Known Activations