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

    Neuronpedia

    INDEX
    Explanations

    keywords related to news and events, particularly involving locations and specific topics like sports and political figures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to media and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rail
    -0.82
    ad
    -0.82
    ord
    -0.81
    lahoma
    -0.79
    idi
    -0.76
    aron
    -0.76
    orn
    -0.75
    roman
    -0.74
    orio
    -0.73
    adem
    -0.73
    POSITIVE LOGITS
    BOOK
    1.40
    HEAD
    1.38
    DOWN
    1.34
    ING
    1.33
    LY
    1.33
    IES
    1.31
    BALL
    1.30
     EDITION
    1.28
    AGE
    1.28
     WITH
    1.27
    Act Density 0.089%

    No Known Activations