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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "significant."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "significant."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nery
    -0.85
    yer
    -0.81
    elf
    -0.79
    creen
    -0.76
    ©¶æ
    -0.75
    ners
    -0.75
    chers
    -0.75
    tein
    -0.75
    heim
    -0.72
    iverpool
    -0.72
    POSITIVE LOGITS
     amounts
    1.03
     amount
    0.95
    itarian
    0.91
     portions
    0.85
     understatement
    0.80
     quantities
    0.80
     importance
    0.78
     imped
    0.78
     impact
    0.77
     chunks
    0.75
    Act Density 0.037%

    No Known Activations