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

    Neuronpedia

    INDEX
    Explanations

    mentions of colleagues and themes related to colonialism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lings
    -0.16
    kova
    -0.16
    ultur
    -0.15
    ris
    -0.15
    ald
    -0.15
    ouch
    -0.15
    wald
    -0.15
     Hao
    -0.15
    illance
    -0.14
    elerik
    -0.14
    POSITIVE LOGITS
    ombo
    0.22
    onna
    0.19
    /un
    0.19
    iseum
    0.18
    cy
    0.18
    apsed
    0.17
    worth
    0.16
    pedia
    0.15
    gate
    0.15
     Carm
    0.15
    Act Density 0.051%

    No Known Activations