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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "few"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "few" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Terrorism
    -0.68
    apist
    -0.64
    mop
    -0.63
    agnar
    -0.63
     Noir
    -0.63
     accordingly
    -0.63
     indo
    -0.63
    ICO
    -0.63
     masculinity
    -0.61
    soc
    -0.59
    POSITIVE LOGITS
     hundred
    1.05
    est
    1.04
     dozen
    0.94
    een
    0.89
     thousand
    0.86
    ples
    0.80
     ILCS
    0.80
    ãĤ£
    0.79
     cents
    0.76
    ishers
    0.75
    Act Density 0.022%

    No Known Activations