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

    Neuronpedia

    INDEX
    Explanations

    references to crimes, particularly violent offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walkover
    -0.63
    TagMode
    -0.63
    +#+#
    -0.57
    growing
    -0.55
    thaler
    -0.53
     growing
    -0.51
    temon
    -0.51
     gynhyrchwyd
    -0.50
    ướt
    -0.50
    elon
    -0.49
    POSITIVE LOGITS
    ConstraintMaker
    0.58
     accused
    0.56
     arrested
    0.56
     acusado
    0.56
    tagHelper
    0.55
     remanded
    0.53
     allegedly
    0.53
     suspected
    0.51
     indicted
    0.50
    StoryboardSegue
    0.49
    Act Density 0.436%

    No Known Activations