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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative impacts or severe consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote significant negative impacts or setbacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.81
    cius
    -0.62
    nesota
    -0.61
     branches
    -0.61
     Halls
    -0.61
     calendars
    -0.60
     ancestors
    -0.59
     channels
    -0.58
     Empires
    -0.58
    cients
    -0.57
    POSITIVE LOGITS
    hearted
    0.97
    blow
    0.94
    hard
    0.92
    warming
    0.89
     against
    0.86
    pun
    0.86
     inflicted
    0.83
    ingly
    0.81
    wart
    0.81
    warm
    0.80
    Act Density 0.076%

    No Known Activations