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

    Neuronpedia

    INDEX
    Explanations

    references to political threats and changes in societal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nuru
    -0.15
    pone
    -0.15
    /rfc
    -0.15
    quam
    -0.14
    leo
    -0.14
     Affero
    -0.14
    -ÑĤеÑħ
    -0.14
     ÑģÑĤо
    -0.14
    verty
    -0.14
    ÅĻád
    -0.14
    POSITIVE LOGITS
     Brexit
    0.21
     Donald
    0.16
     Trump
    0.16
     nat
    0.16
     antid
    0.15
    345
    0.15
     Europe
    0.14
    rep
    0.14
    Donald
    0.14
    ism
    0.14
    Act Density 0.083%

    No Known Activations