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

    Neuronpedia

    INDEX
    Explanations

    words related to intense anger or fury

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of rage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramer
    -0.87
    herty
    -0.79
    icut
    -0.79
    metics
    -0.70
    rica
    -0.69
    roma
    -0.68
    ipment
    -0.64
    akeru
    -0.64
    essee
    -0.64
     Amend
    -0.64
    POSITIVE LOGITS
    quit
    1.17
     rage
    1.03
     fury
    0.91
     raging
    0.87
     indignation
    0.83
     furnace
    0.81
     vengeance
    0.77
    bol
    0.75
     raged
    0.74
    ous
    0.74
    Act Density 0.022%

    No Known Activations