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

    Neuronpedia

    INDEX
    Explanations

    references to political ideologies, particularly those associated with the left and right

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jee
    -0.17
    actal
    -0.17
    uled
    -0.16
     fisse
    -0.15
    .inflate
    -0.15
    ossal
    -0.15
    jure
    -0.15
    ipers
    -0.15
    ration
    -0.15
    anse
    -0.15
    POSITIVE LOGITS
     wing
    0.41
    -wing
    0.40
    wing
    0.39
     Wing
    0.33
    ward
    0.32
    翼
    0.29
    ist
    0.29
    ists
    0.28
     wings
    0.27
    -leaning
    0.25
    Act Density 0.009%

    No Known Activations