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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a large or significant quantity or amount

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantity or amount

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.80
    Ħ¢
    -0.76
    farious
    -0.74
    irie
    -0.68
    Ń·
    -0.67
    rador
    -0.67
    displayText
    -0.66
    rir
    -0.66
    wcsstore
    -0.66
    oche
    -0.65
    POSITIVE LOGITS
     accomplishment
    1.01
     compared
    1.00
     achievement
    0.95
     odds
    0.93
     considering
    0.93
     exaggeration
    0.90
     margin
    0.84
     understatement
    0.82
     (~
    0.82
     feat
    0.82
    Act Density 0.241%

    No Known Activations