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

    Neuronpedia

    INDEX
    Explanations

    words related to grilling or causing harm/violence

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the verb "kill" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     critically
    -0.68
     IEEE
    -0.65
    Pros
    -0.64
     peer
    -0.63
    trop
    -0.62
    chrome
    -0.61
     Bet
    -0.60
     PRES
    -0.59
    Barn
    -0.58
    BOOK
    -0.58
    POSITIVE LOGITS
    illing
    1.19
    espie
    0.97
    illed
    0.94
    sburg
    0.89
    iatus
    0.86
     horizont
    0.85
    ills
    0.80
    ustration
    0.80
    imentary
    0.79
    iard
    0.78
    Act Density 0.004%

    No Known Activations