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

    Neuronpedia

    INDEX
    Explanations

    phrases related to layouts and designs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Khart
    -0.84
     Darío
    -0.83
     Juf
    -0.82
     Mlle
    -0.81
     migli
    -0.78
     Immig
    -0.78
     Malte
    -0.78
     embra
    -0.78
     Intere
    -0.77
     Hez
    -0.77
    POSITIVE LOGITS
     changes
    0.60
     layout
    0.59
     patterns
    0.58
    布局
    0.56
     pattern
    0.56
     changed
    0.55
     habits
    0.55
     arrangements
    0.54
     utafitiHapana
    0.54
     assumptions
    0.54
    Act Density 0.449%

    No Known Activations