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

    Neuronpedia

    INDEX
    Explanations

    references to time or temporal markers

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

    occurrences of "later"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.69
     snippetHide
    -0.54
    WriteTagHelper
    -0.54
    setupUi
    -0.53
    ConstraintMaker
    -0.51
    oneofs
    -0.48
    Portail
    -0.44
    Autoritní
    -0.43
     pageContext
    -0.42
    createCanvas
    -0.42
    POSITIVE LOGITS
     later
    1.17
     später
    1.13
    later
    1.09
    Later
    1.07
     Later
    1.05
     späteren
    0.96
     senere
    0.95
     pozdě
    0.93
     LATER
    0.93
     позже
    0.88
    Act Density 0.129%

    No Known Activations