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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "same" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     at
    -0.19
    rico
    -0.17
     èĩ³
    -0.17
    ride
    -0.16
    imum
    -0.15
    AMS
    -0.15
    ponsors
    -0.14
    èĩ³
    -0.14
    At
    -0.14
     ðŁĺī↵↵
    -0.14
    POSITIVE LOGITS
     time
    0.38
    .time
    0.24
    time
    0.23
     اÙĦÙĪÙĤت
    0.22
     TIME
    0.22
    æŶéĹ´
    0.22
     tiempo
    0.22
    =time
    0.21
    _time
    0.21
    ertime
    0.20
    Act Density 0.016%

    No Known Activations