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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violence and aggression

    oai_token-act-pair · gpt-3.5-turbo

    references to war or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.89
    atown
    -0.71
    ruary
    -0.70
    ĸļ
    -0.69
    cribed
    -0.69
     Volunte
    -0.68
    ISTORY
    -0.67
    olkien
    -0.66
    anship
    -0.65
    zed
    -0.65
    POSITIVE LOGITS
     crap
    1.16
     entire
    1.12
     messenger
    1.09
     offending
    1.06
     throats
    1.01
     intruder
    1.01
     opponent
    1.00
     unsuspecting
    0.97
     innocent
    0.94
     enemy
    0.93
    Act Density 0.266%

    No Known Activations