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

    Neuronpedia

    INDEX
    Explanations

    phrases related to international politics and agreements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.83
    coins
    -0.81
    marks
    -0.78
    stars
    -0.77
    !/
    -0.76
     Jagu
    -0.76
    eyes
    -0.75
    ographs
    -0.75
    Arcade
    -0.73
    âĿ
    -0.73
    POSITIVE LOGITS
     plethora
    1.11
     comprehensive
    1.06
     slew
    1.06
     forthcoming
    1.06
    rouse
    1.05
     sizeable
    1.05
     lengthy
    1.01
     massive
    1.01
    usterity
    1.01
     controversial
    1.00
    Act Density 0.775%

    No Known Activations