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

    Neuronpedia

    INDEX
    Explanations

    the word "and" in various contexts and its relationship to other words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erder
    -0.44
    ective
    -0.44
    tiérrez
    -0.43
    DIPSETTING
    -0.43
     '\\;'
    -0.42
     Gemeins
    -0.41
     Arabian
    -0.41
     Familienname
    -0.41
    IKAN
    -0.40
    봅
    -0.40
    POSITIVE LOGITS
    MemoryWarning
    0.59
     moeite
    0.54
     money
    0.51
     laughter
    0.50
     ink
    0.48
     grime
    0.48
     oči
    0.47
    verwijspagina
    0.47
     pieniądze
    0.47
     fury
    0.47
    Act Density 0.512%

    No Known Activations