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

    Neuronpedia

    INDEX
    Explanations

    phrases related to goals and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ila
    -0.15
    kart
    -0.15
    deaux
    -0.15
    طب
    -0.15
    ype
    -0.15
    zac
    -0.14
    çĩķ
    -0.14
    alsa
    -0.14
    Mgr
    -0.14
    wu
    -0.14
    POSITIVE LOGITS
     Glo
    0.16
     Dil
    0.15
    porto
    0.15
    å¾ģ
    0.14
     dilation
    0.14
     ineff
    0.14
     dil
    0.14
    366
    0.14
    rott
    0.14
    luk
    0.13
    Act Density 0.120%

    No Known Activations