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

    Neuronpedia

    INDEX
    Explanations

    stories related to crime and legal issues

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and crime in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }}}
    -0.69
    ":["
    -0.69
    ministic
    -0.69
    olars
    -0.68
    ernels
    -0.66
     Languages
    -0.65
    /+
    -0.64
    DragonMagazine
    -0.63
    ":"/
    -0.63
    Region
    -0.62
    POSITIVE LOGITS
     allegedly
    1.02
     accidentally
    0.91
     alleged
    0.85
     wrongly
    0.83
     improperly
    0.83
     overheard
    0.83
     leaked
    0.82
     abusive
    0.81
     gunman
    0.81
    andals
    0.80
    Act Density 1.507%

    No Known Activations