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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating gratitude or requests for action

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing intentions or desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    furt
    -0.69
    VERTISEMENT
    -0.66
    proof
    -0.64
     Stru
    -0.64
    grounds
    -0.63
    Got
    -0.63
    metadata
    -0.63
    ById
    -0.61
    bars
    -0.61
    hes
    -0.61
    POSITIVE LOGITS
     emulate
    1.14
     recreate
    1.08
     propose
    1.04
     participate
    1.00
     partake
    0.94
     preserve
    0.94
     nominate
    0.92
     abolish
    0.92
     share
    0.91
     marry
    0.90
    Act Density 0.076%

    No Known Activations