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

    Neuronpedia

    INDEX
    Explanations

    instances of political power dynamics and historical political events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    хьтан
    -0.69
    Abp
    -0.54
    <?
    -0.53
    \}\\
    -0.52
     métiers
    -0.49
    Carriera
    -0.49
    󠁢
    -0.48
    ArrowToggle
    -0.48
    icap
    -0.47
     illustre
    -0.47
    POSITIVE LOGITS
     personally
    1.09
     persönlich
    0.90
     ordering
    0.84
    สั่ง
    0.80
     personalmente
    0.80
    亲自
    0.78
     Personally
    0.75
     overseeing
    0.75
     preside
    0.73
     orders
    0.73
    Act Density 0.459%

    No Known Activations