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

    Neuronpedia

    INDEX
    Explanations

    references to crime and criminal behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XtraEditors
    -0.65
    httphttps
    -0.57
    SizeMode
    -0.52
     оригіналу
    -0.52
     víctimas
    -0.50
    Victim
    -0.50
    '])->
    -0.49
    '],$
    -0.49
    受害
    -0.49
    volmente
    -0.49
    POSITIVE LOGITS
     criminals
    0.96
     murderers
    0.78
     terrorists
    0.76
     villains
    0.75
     thieves
    0.73
     serial
    0.73
     killers
    0.73
     perpetrators
    0.71
     culprits
    0.71
     murderer
    0.70
    Act Density 0.528%

    No Known Activations