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

    Neuronpedia

    INDEX
    Explanations

    instances of vandalism or related actions

    oai_token-act-pair · gpt-3.5-turbo

    incidents of vandalism and related criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dinand
    -0.79
    amacare
    -0.73
    umbo
    -0.72
    vana
    -0.72
    croft
    -0.72
    urion
    -0.70
    berman
    -0.69
     BMI
    -0.68
    aucas
    -0.67
    ramer
    -0.66
    POSITIVE LOGITS
     vandalism
    1.12
     spree
    0.95
     graffiti
    0.91
     vandal
    0.89
     leve
    0.85
    andals
    0.72
    adoes
    0.72
     rampage
    0.71
     removal
    0.70
     leveled
    0.70
    Act Density 0.045%

    No Known Activations