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

    Neuronpedia

    INDEX
    Explanations

    words related to being removed from a position of power or authority

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political removal or overthrowing of leaders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingham
    -0.85
    acts
    -0.79
    argo
    -0.69
    opic
    -0.67
    ogens
    -0.66
    atur
    -0.66
    ioxide
    -0.66
    ridges
    -0.65
    etics
    -0.65
    urgy
    -0.64
    POSITIVE LOGITS
     ousted
    1.09
     sacked
    1.04
     embattled
    0.74
     victorious
    0.73
     triumphant
    0.71
     former
    0.69
     disgr
    0.69
     aback
    0.68
     undermin
    0.67
     overthrow
    0.62
    Act Density 0.033%

    No Known Activations