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

    Neuronpedia

    INDEX
    Explanations

    words related to the abbreviation "ca" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to California

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bucks
    -0.84
    geist
    -0.82
    hyde
    -0.81
     GOODMAN
    -0.80
    rition
    -0.77
    */(
    -0.76
    hower
    -0.75
    DragonMagazine
    -0.74
    matter
    -0.74
    âĶģ
    -0.73
    POSITIVE LOGITS
     ca
    1.09
    utes
    0.95
    ffe
    0.89
    ute
    0.85
    ffer
    0.83
    ution
    0.83
    pping
    0.83
    enture
    0.82
    uter
    0.81
    utions
    0.80
    Act Density 0.008%

    No Known Activations