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

    Neuronpedia

    INDEX
    Explanations

    the word "since" indicating a reference to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.59
     Lightboxes
    -0.59
     africains
    -0.58
    chengladbach
    -0.57
    rbrakk
    -0.57
     ferons
    -0.55
     Alembic
    -0.52
     témoig
    -0.52
    chieht
    -0.52
     tfsi
    -0.51
    POSITIVE LOGITS
    Whenever
    0.60
     Whenever
    0.58
     whenever
    0.57
    whenever
    0.56
    Ever
    0.55
     EVER
    0.54
     ever
    0.54
     Ever
    0.52
    ever
    0.52
     FOREVER
    0.46
    Act Density 0.001%

    No Known Activations