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

    Neuronpedia

    INDEX
    Explanations

    temporal references indicating sequences or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchen
    -0.16
     lately
    -0.15
     upcoming
    -0.15
     rok
    -0.14
    alic
    -0.14
    irse
    -0.14
    ä¹ħ
    -0.14
    shaw
    -0.14
     recently
    -0.13
     sooner
    -0.13
    POSITIVE LOGITS
     publication
    0.24
    word
    0.22
     news
    0.22
     their
    0.21
     word
    0.19
     its
    0.19
    words
    0.18
    publication
    0.17
     receipt
    0.17
     receiving
    0.16
    Act Density 0.097%

    No Known Activations