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

    Neuronpedia

    INDEX
    Explanations

    phrases related to activities and actions involving food or cooking

    oai_token-act-pair · gpt-3.5-turbo

    issues related to health and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĶ°
    -0.58
    soDeliveryDate
    -0.57
    senal
    -0.55
    xtap
    -0.53
    arij
    -0.50
    staking
    -0.48
    ovie
    -0.47
    YN
    -0.46
    JM
    -0.46
    published
    -0.46
    POSITIVE LOGITS
     anymore
    0.70
     or
    0.67
    .''.
    0.67
    ,''
    0.61
    .''
    0.61
     etc
    0.59
     without
    0.59
     outdoors
    0.57
    .</
    0.57
     safely
    0.57
    Act Density 1.382%

    No Known Activations