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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of being "out", such as "outgrowth" or "outlier"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating "out" related concepts or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arsen
    -0.69
     tyr
    -0.67
     0004
    -0.63
    avorite
    -0.59
     Brach
    -0.59
     Pry
    -0.58
     Puzzles
    -0.58
    elsius
    -0.58
     Mub
    -0.58
     etched
    -0.57
    POSITIVE LOGITS
    stretched
    1.34
    lander
    1.18
    fitted
    1.17
    flows
    1.13
    smart
    1.12
    fitting
    1.09
    casts
    1.09
    lier
    1.05
    dated
    1.05
    lying
    1.04
    Act Density 0.052%

    No Known Activations