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

    Neuronpedia

    INDEX
    Explanations

    political and social action phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of political engagement and community involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ;;;;;;;;
    -0.62
     Moroc
    -0.62
    bourg
    -0.62
    never
    -0.61
    nown
    -0.59
     mars
    -0.58
     drowned
    -0.58
     accordingly
    -0.58
    00007
    -0.57
     Neh
    -0.57
    POSITIVE LOGITS
    irtual
    0.65
    GROUP
    0.61
    issan
    0.59
    esta
    0.58
    pires
    0.57
     these
    0.57
    lict
    0.57
    cery
    0.56
     comes
    0.55
     hindsight
    0.55
    Act Density 0.326%

    No Known Activations