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

    Neuronpedia

    INDEX
    Explanations

    locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Rotterdam" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indisc
    -0.62
     Pace
    -0.62
     undermin
    -0.61
    ा
    -0.61
    ĪĴ
    -0.59
    ï¸
    -0.58
    ¬¼
    -0.58
     disparate
    -0.57
    ELS
    -0.57
    isconsin
    -0.56
    POSITIVE LOGITS
    geist
    1.44
    ranean
    1.13
    rane
    1.12
    rors
    1.06
    gom
    1.03
    tainment
    1.02
    dam
    1.01
    flies
    1.00
    rible
    0.98
    brates
    0.92
    Act Density 0.044%

    No Known Activations