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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "later" or variations related to the concept of time progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "later"

    np_acts-logits-general · gemini-2.0-flash

    later

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.61
     pleaſure
    -0.58
     snippetHide
    -0.57
     myſelf
    -0.56
     faſt
    -0.55
    -------
    -0.51
     eſſ
    -0.48
     ochi
    -0.47
    Climate
    -0.47
    jednoc
    -0.47
    POSITIVE LOGITS
    Later
    1.05
    later
    1.05
     later
    1.05
     Later
    1.03
     später
    0.99
     LATER
    0.91
     späteren
    0.79
     Posteriormente
    0.75
     позже
    0.75
     afterward
    0.75
    Act Density 0.166%

    No Known Activations