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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to incidents and events involving violence or emergency situations

    oai_token-act-pair · gpt-3.5-turbo

    events involving violence or crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [/
    -0.65
    ++++++++++++++++
    -0.64
     (&
    -0.62
     '[
    -0.61
    -->
    -0.59
     presupp
    -0.58
    ********************************
    -0.56
    Quote
    -0.56
     yourselves
    -0.56
     tho
    -0.55
    POSITIVE LOGITS
    interstitial
    0.82
     respectively
    0.74
    phrine
    0.59
    acas
    0.55
    76561
    0.54
     precursor
    0.53
    ertility
    0.53
     spa
    0.51
     Mecca
    0.51
     namesake
    0.50
    Act Density 2.272%

    No Known Activations