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

    Neuronpedia

    INDEX
    Explanations

    temporal expressions related to changes and transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¹ħ
    -0.15
     lately
    -0.14
    licht
    -0.14
    uchen
    -0.14
     Recently
    -0.14
    shaw
    -0.14
    haul
    -0.13
    PRS
    -0.13
     recently
    -0.13
    ulumi
    -0.13
    POSITIVE LOGITS
     publication
    0.24
    word
    0.19
    publication
    0.17
     passage
    0.17
     Operation
    0.16
     news
    0.16
     enactment
    0.16
     host
    0.16
     their
    0.16
     word
    0.16
    Act Density 0.167%

    No Known Activations