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

    Neuronpedia

    INDEX
    Explanations

    references to political events and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adro
    -0.17
    resa
    -0.16
    ottes
    -0.15
    \common
    -0.14
    immers
    -0.14
    ware
    -0.14
    avia
    -0.14
     submarines
    -0.14
    resas
    -0.14
    apy
    -0.14
    POSITIVE LOGITS
     Capitol
    0.33
     riot
    0.29
     mob
    0.28
     Proud
    0.26
    Cap
    0.25
     ins
    0.23
     Riot
    0.23
    mob
    0.22
     riots
    0.22
     storm
    0.21
    Act Density 0.022%

    No Known Activations