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

    Neuronpedia

    INDEX
    Explanations

    evidence related to various topics, such as construction work, military presence, negotiation, culture, security concerns, misconduct, crime, and injuries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evidence of wrongdoing or legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wheelchair
    -0.69
     reins
    -0.68
    adle
    -0.65
    utterstock
    -0.64
    adobe
    -0.62
    aughters
    -0.61
     Nare
    -0.58
     Dram
    -0.57
    verts
    -0.56
    liam
    -0.55
    POSITIVE LOGITS
    worthiness
    1.16
     wrongdoing
    1.14
     intentions
    1.00
     involvement
    0.99
     imminent
    0.95
     irregularities
    0.95
     impending
    0.95
     complicity
    0.92
     tampering
    0.90
     criminality
    0.90
    Act Density 0.597%

    No Known Activations