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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time periods and historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avors
    -0.15
    olleyError
    -0.14
    izer
    -0.14
    brook
    -0.14
    ropolis
    -0.13
    æº
    -0.13
     breeze
    -0.13
    yscale
    -0.13
    ç¢
    -0.13
     Rebels
    -0.13
    POSITIVE LOGITS
     reign
    0.25
     height
    0.24
     Second
    0.20
     tenure
    0.19
     Height
    0.19
     Reign
    0.18
     hey
    0.18
    Second
    0.17
    Height
    0.17
    hey
    0.17
    Act Density 0.071%

    No Known Activations