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

    Neuronpedia

    INDEX
    Explanations

    terms related to political ideologies, particularly liberalism and conservatism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aday
    -0.16
    jee
    -0.15
    ose
    -0.15
    VEC
    -0.15
    istrovstvÃŃ
    -0.15
    rei
    -0.15
    .INSTANCE
    -0.14
    ings
    -0.14
    ee
    -0.14
    ÑĢек
    -0.14
    POSITIVE LOGITS
    -leaning
    0.28
    /lib
    0.27
    -lib
    0.18
     credentials
    0.17
    -rad
    0.17
    -minded
    0.17
    lero
    0.16
    ød
    0.16
    jerne
    0.16
    ness
    0.16
    Act Density 0.046%

    No Known Activations