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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "significant" and similar terms indicating importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.99
    elf
    -0.79
    iverpool
    -0.78
    yer
    -0.78
    nery
    -0.74
    bable
    -0.70
    called
    -0.68
    keeper
    -0.67
    stein
    -0.67
    eez
    -0.66
    POSITIVE LOGITS
     amounts
    1.17
    itarian
    1.16
     amount
    1.08
     portions
    0.99
     understatement
    0.97
     quantities
    0.97
     improvement
    0.95
     imped
    0.90
     differences
    0.89
     difference
    0.89
    Act Density 0.058%

    No Known Activations