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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to changes or movements

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to changes or transitions in policies and funding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Eva
    -0.81
     Frie
    -0.68
    Ñı
    -0.67
    fect
    -0.67
    Result
    -0.65
    Perfect
    -0.65
    Sensor
    -0.65
     Janeiro
    -0.65
    spot
    -0.62
     Correspond
    -0.62
    POSITIVE LOGITS
     moratorium
    1.01
     altogether
    0.84
     outright
    0.77
     arsen
    0.75
     abol
    0.75
     bans
    0.74
     abolished
    0.73
     downs
    0.72
    ansk
    0.72
     decriminal
    0.72
    Act Density 0.463%

    No Known Activations