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

    Neuronpedia

    INDEX
    Explanations

    words related to criminal activities and charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kas
    -0.16
     susp
    -0.15
    ulous
    -0.15
     иÑģполн
    -0.15
     arrest
    -0.14
     suspend
    -0.14
    loff
    -0.14
    olley
    -0.14
     quar
    -0.14
    ariat
    -0.14
    POSITIVE LOGITS
     conspiracy
    0.23
     wire
    0.22
     Hob
    0.22
     Honest
    0.21
     Wire
    0.20
     interstate
    0.20
     Conspiracy
    0.19
     obstruction
    0.19
    wire
    0.18
     hob
    0.18
    Act Density 0.026%

    No Known Activations