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

    Neuronpedia

    INDEX
    Explanations

    phrases related to incidents or events breaking out

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "broke" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     appell
    -0.67
    course
    -0.66
     attendant
    -0.64
    Applic
    -0.63
    respective
    -0.63
    ctions
    -0.62
    imum
    -0.62
     Analog
    -0.61
    ï¸
    -0.61
    MN
    -0.61
    POSITIVE LOGITS
     broke
    3.51
     breaks
    1.82
     break
    1.70
     breaking
    1.61
     broken
    1.54
     tore
    1.46
     busted
    1.38
     shattered
    1.31
     blew
    1.31
     cracked
    1.30
    Act Density 0.011%

    No Known Activations