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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "and" in combination with a variety of other words

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and their associated phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ...)
    -0.70
     Moss
    -0.64
     Magn
    -0.63
    )--
    -0.62
     .)
    -0.61
     Axel
    -0.60
     Nap
    -0.59
    —"
    -0.58
     Sass
    -0.58
     Mash
    -0.58
    POSITIVE LOGITS
    etheless
    1.00
    summary
    0.83
    ensation
    0.81
    obar
    0.79
    ernel
    0.75
    yip
    0.74
    inen
    0.72
    values
    0.72
    ogether
    0.72
    ovie
    0.69
    Act Density 0.376%

    No Known Activations