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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to physical injuries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zee
    -0.77
    zees
    -0.76
    avanaugh
    -0.71
    ullivan
    -0.71
    rows
    -0.71
    ILE
    -0.71
    @@@@
    -0.69
    itudes
    -0.66
    ģĸ
    -0.66
    ihu
    -0.66
    POSITIVE LOGITS
     prevention
    0.92
     inflicted
    0.91
     injury
    0.89
     incurred
    0.84
     prone
    0.82
     replacements
    0.82
     injuries
    0.80
     suffered
    0.79
     riddled
    0.79
     plagued
    0.78
    Act Density 0.027%

    No Known Activations