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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals involved in criminal activities or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.05
    2:0.02
    3:0.12
    4:0.21
    5:0.07
    6:0.07
    7:0.07
    8:0.09
    9:0.04
    10:0.02
    11:0.05
    Negative Logits
    artisan
    -2.59
    ipedia
    -2.06
     certs
    -2.00
    issions
    -1.98
    soDeliveryDate
    -1.95
    kefeller
    -1.92
    apps
    -1.91
    parency
    -1.90
    ��極
    -1.84
     administrations
    -1.83
    POSITIVE LOGITS
     assaulted
    1.98
     Victim
    1.88
     assailant
    1.84
     followed
    1.83
    gdala
    1.82
     hospitalized
    1.79
     bystand
    1.76
     intruder
    1.74
     awoke
    1.72
     suspended
    1.71
    Act Density 0.010%

    No Known Activations