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

    Neuronpedia

    INDEX
    Explanations

    elements related to governance and authority structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ntag
    -0.21
    owi
    -0.19
    ernet
    -0.17
    erland
    -0.16
    ären
    -0.15
    ghi
    -0.15
    ambia
    -0.15
    igel
    -0.14
    ato
    -0.14
    iegel
    -0.14
    POSITIVE LOGITS
    ifetime
    0.15
    etch
    0.14
    ü
    0.14
     uns
    0.14
    246
    0.14
    raman
    0.14
     dest
    0.14
    801
    0.14
    569
    0.13
    zek
    0.13
    Act Density 0.139%

    No Known Activations