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

    Neuronpedia

    INDEX
    Explanations

    adjectives expressing a high level of importance or impact

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "significant."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.88
    nery
    -0.85
    elf
    -0.84
    yer
    -0.80
    iverpool
    -0.75
    heim
    -0.75
    tein
    -0.75
    creen
    -0.74
    chers
    -0.72
    spr
    -0.71
    POSITIVE LOGITS
     amounts
    1.13
     amount
    1.03
    itarian
    0.95
     portions
    0.91
     quantities
    0.86
     understatement
    0.84
     importance
    0.82
     imped
    0.81
     impact
    0.80
     chunks
    0.80
    Act Density 0.037%

    No Known Activations