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

    Neuronpedia

    INDEX
    Explanations

    phrases related to breaking laws or rules

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "breaking" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imental
    -0.72
    ulp
    -0.69
    uther
    -0.68
    gel
    -0.67
    oft
    -0.66
    minist
    -0.65
    apixel
    -0.65
    oka
    -0.65
    ateur
    -0.64
    affer
    -0.63
    POSITIVE LOGITS
    neck
    0.92
    breakers
    0.89
    breaks
    0.87
    break
    0.83
     break
    0.80
     necks
    0.79
    staff
    0.79
     broke
    0.76
    breaking
    0.76
     breaks
    0.75
    Act Density 0.026%

    No Known Activations