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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate changes or comparisons in statistics or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĶ¨åĵģ
    -0.17
    .Logf
    -0.17
    ceb
    -0.16
    addError
    -0.15
    #Region
    -0.14
    eriod
    -0.14
     TMPro
    -0.14
    iesen
    -0.14
    ève
    -0.13
    _STD
    -0.13
    POSITIVE LOGITS
     levels
    0.31
     Levels
    0.25
    levels
    0.25
    Levels
    0.22
     level
    0.20
     nive
    0.19
     record
    0.19
    _levels
    0.18
     nearly
    0.17
     highs
    0.17
    Act Density 0.039%

    No Known Activations