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

    Neuronpedia

    INDEX
    Explanations

    phrases related to supporting a cause or belief

    oai_token-act-pair · gpt-3.5-turbo

    references to causes, ideals, and political messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ursed
    -0.65
     Kers
    -0.62
     PIT
    -0.62
    inka
    -0.59
     Ravens
    -0.59
    arling
    -0.59
    leep
    -0.59
    administ
    -0.58
    aband
    -0.58
    ãĥĥãĥĪ
    -0.58
    POSITIVE LOGITS
    geist
    0.89
     creed
    0.87
    ologies
    0.85
     ideals
    0.85
    ifice
    0.83
     worldview
    0.77
     ideology
    0.76
     championed
    0.75
     dogma
    0.75
     preached
    0.74
    Act Density 0.210%

    No Known Activations