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

    Neuronpedia

    INDEX
    Explanations

    locations and physical settings related to crime and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eries
    -0.65
    osponsors
    -0.62
    assadors
    -0.61
    icent
    -0.60
    utations
    -0.59
    -)
    -0.59
    natureconservancy
    -0.59
    shows
    -0.58
    yss
    -0.58
     dearly
    -0.57
    POSITIVE LOGITS
     injuring
    0.85
     allegedly
    0.77
     undet
    0.73
     altercation
    0.71
     shortly
    0.71
    .[
    0.69
     Frie
    0.69
     intoxicated
    0.68
     drunk
    0.68
     robbery
    0.67
    Act Density 0.320%

    No Known Activations