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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional phrases and the concept of timing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     at
    -0.16
    ÙĬرÙĬ
    -0.14
     pattern
    -0.14
    grav
    -0.14
    åľ°åĮº
    -0.14
    abox
    -0.14
     pathway
    -0.13
    arez
    -0.13
     Pattern
    -0.13
    oline
    -0.13
    POSITIVE LOGITS
     jun
    0.34
     expense
    0.32
     level
    0.32
     intervals
    0.28
     helm
    0.27
    expense
    0.26
     glance
    0.25
     rate
    0.25
     discretion
    0.25
     pace
    0.24
    Act Density 0.290%

    No Known Activations