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

    Neuronpedia

    INDEX
    Explanations

    words related to physical damage or destruction

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word related to damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arist
    -0.83
    atorial
    -0.80
    atography
    -0.76
    pol
    -0.72
    ult
    -0.72
    batch
    -0.72
    ffic
    -0.70
    analysis
    -0.70
    rouse
    -0.70
    ingham
    -0.70
    POSITIVE LOGITS
     damaged
    1.13
     damage
    0.90
     repair
    0.86
     undermin
    0.85
     wounds
    0.81
     warheads
    0.80
     damages
    0.80
     salvage
    0.78
     repairing
    0.78
     tiss
    0.77
    Act Density 0.009%

    No Known Activations