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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize a large or unspecified number of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "countless."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.80
    adish
    -0.74
    emb
    -0.72
    afort
    -0.69
    earance
    -0.67
    atem
    -0.66
    asy
    -0.66
    perse
    -0.65
    acus
    -0.64
    alach
    -0.64
    POSITIVE LOGITS
    ãĤ§
    0.87
     thousands
    0.85
    ãĥ¼ãĥĨãĤ£
    0.82
     millions
    0.81
    åŃIJ
    0.81
    THING
    0.80
     billions
    0.76
    ãĥĺ
    0.74
     kilometers
    0.73
    ãĤ¼ãĤ¦ãĤ¹
    0.72
    Act Density 0.015%

    No Known Activations