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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms related to items, quantities, or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALLY
    -0.69
    nee
    -0.67
    ctor
    -0.66
    rick
    -0.61
     Smile
    -0.61
    riad
    -0.59
    Harris
    -0.59
    Honest
    -0.56
    ãĤ¶
    -0.55
    Hum
    -0.55
    POSITIVE LOGITS
    poons
    1.13
    mith
    1.05
    pread
    0.96
    paces
    0.94
     themselves
    0.94
    hare
    0.93
    hips
    0.90
    ystem
    0.86
    isters
    0.84
    avers
    0.83
    Act Density 0.472%

    No Known Activations