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

    Neuronpedia

    INDEX
    Explanations

    details of criminal activities and charges

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving legal charges or criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reviewers
    -0.71
     strat
    -0.66
     delve
    -0.64
    âĨij
    -0.62
     Chaser
    -0.61
    ).[
    -0.61
     Authors
    -0.60
     thesis
    -0.59
    ".[
    -0.58
     edit
    -0.57
    POSITIVE LOGITS
    adena
    0.80
    married
    0.79
    quartered
    0.78
    iewicz
    0.76
    veland
    0.74
    monton
    0.72
    susp
    0.70
    eret
    0.69
    brother
    0.69
    ameda
    0.68
    Act Density 0.484%

    No Known Activations