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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to lists and organizing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    بوابة
    -0.58
     points
    -0.55
     hits
    -0.54
     
    -0.53
    Clik
    -0.53
     charges
    -0.53
    DoubleQuotes
    -0.50
    facts
    -0.49
    intellij
    -0.49
     puntos
    -0.48
    POSITIVE LOGITS
     bibliographies
    1.19
    Lists
    1.18
     atmospheres
    1.18
    LISTS
    1.12
     environments
    1.11
     universes
    1.09
     Lists
    1.08
    lists
    1.08
     climates
    1.07
     budgets
    1.06
    Act Density 0.300%

    No Known Activations