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

    Neuronpedia

    INDEX
    Explanations

    sequences related to beginnings, transitions, or references to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħn
    -0.14
    le
    -0.14
    roz
    -0.14
    atur
    -0.14
    .Navigator
    -0.14
    ล
    -0.14
     æ¯Ķ
    -0.13
    ogr
    -0.13
    raphic
    -0.13
    ÙĥÙĨ
    -0.13
    POSITIVE LOGITS
     beginning
    0.30
     start
    0.28
     from
    0.26
     top
    0.24
    soup
    0.24
    FromClass
    0.23
    	from
    0.23
     From
    0.22
     soup
    0.22
     stem
    0.22
    Act Density 0.052%

    No Known Activations