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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to revolutions and social movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    visor
    -0.16
    -uri
    -0.15
    opi
    -0.15
    xor
    -0.15
    marks
    -0.15
    comings
    -0.15
    actors
    -0.15
    oux
    -0.14
    rib
    -0.14
    oba
    -0.14
    POSITIVE LOGITS
    aries
    0.22
    -era
    0.19
    arily
    0.18
    naire
    0.17
    aire
    0.16
    ropa
    0.15
    -leaning
    0.15
    ively
    0.15
    rad
    0.15
     Against
    0.14
    Act Density 0.058%

    No Known Activations