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

    Neuronpedia

    INDEX
    Explanations

    references to political leaders in positions of power

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.84
    eros
    -0.81
    wed
    -0.72
    ersion
    -0.71
     mountainous
    -0.69
    entric
    -0.69
    zl
    -0.68
    skilled
    -0.68
    اÙĦ
    -0.66
    rawdownloadcloneembedreportprint
    -0.66
    POSITIVE LOGITS
     Leader
    0.86
     Mitch
    0.78
     Trey
    0.76
    chief
    0.74
    aroo
    0.73
    itol
    0.72
    stration
    0.70
     negotiator
    0.70
    ebus
    0.69
     Yon
    0.69
    Act Density 0.022%

    No Known Activations