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

    Neuronpedia

    INDEX
    Explanations

    references to genocides and related atrocities throughout history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BN
    -0.16
    uke
    -0.15
    代
    -0.15
    ñana
    -0.14
    -ra
    -0.14
    sets
    -0.14
    uctor
    -0.14
    ystate
    -0.14
    jet
    -0.14
    umb
    -0.14
    POSITIVE LOGITS
    agos
    0.16
    cci
    0.14
    ulling
    0.14
    etin
    0.14
    AVA
    0.14
    okit
    0.14
    NamedQuery
    0.14
    417
    0.13
    ekt
    0.13
    elli
    0.13
    Act Density 0.018%

    No Known Activations