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

    Neuronpedia

    INDEX
    Explanations

    the word "one" in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "one" or unity among groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acements
    -0.70
    cases
    -0.66
    soDeliveryDate
    -0.66
    ãĤ¤ãĥĪ
    -0.66
    ories
    -0.64
    ooks
    -0.64
    letters
    -0.64
    oof
    -0.63
    ãĥ©ãĥ³
    -0.63
    cakes
    -0.62
    POSITIVE LOGITS
     side
    0.88
     particular
    0.86
     hundred
    0.84
     sided
    0.83
     person
    0.83
     aspect
    0.78
     thousand
    0.75
     hemisphere
    0.74
     Hundred
    0.74
     thing
    0.74
    Act Density 0.127%

    No Known Activations