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

    Neuronpedia

    INDEX
    Explanations

    words related to breaking or destruction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "breaking" or significant disruptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uther
    -0.80
    GY
    -0.75
    ulp
    -0.72
    minist
    -0.69
    nery
    -0.67
    ammy
    -0.66
    metics
    -0.66
    igmat
    -0.64
    iquid
    -0.63
    ality
    -0.63
    POSITIVE LOGITS
    breakers
    0.95
     breaking
    0.94
    break
    0.88
     broke
    0.85
    breaking
    0.83
     break
    0.80
     breaks
    0.74
    breaks
    0.73
     necks
    0.73
    lyn
    0.70
    Act Density 0.011%

    No Known Activations