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

    Neuronpedia

    INDEX
    Explanations

    references to "vice" and its variations in the context of leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Minute
    -0.15
    οÏħÏģγ
    -0.15
    виÑĩ
    -0.15
    antz
    -0.14
    .onViewCreated
    -0.14
    çĥ
    -0.14
    etter
    -0.14
    anken
    -0.13
    иÑĤÑĭ
    -0.13
    inery
    -0.13
    POSITIVE LOGITS
     versa
    0.31
    ger
    0.16
    -president
    0.16
     Sokol
    0.16
    586
    0.15
    ward
    0.15
    iple
    0.15
    ante
    0.15
    -vers
    0.14
    ories
    0.14
    Act Density 0.012%

    No Known Activations