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

    Neuronpedia

    INDEX
    Explanations

    references to political promises and the resulting actions that follow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hausen
    -0.17
    Ưá»
    -0.14
    ]init
    -0.14
     поÑħ
    -0.14
     prze
    -0.14
    DataProvider
    -0.14
    mür
    -0.14
    merce
    -0.14
    ions
    -0.14
    SSIP
    -0.14
    POSITIVE LOGITS
     dependence
    0.25
     reliance
    0.24
     era
    0.24
     remaining
    0.23
     decades
    0.22
     vest
    0.22
     practice
    0.21
     existing
    0.20
     hold
    0.20
     Era
    0.20
    Act Density 0.209%

    No Known Activations