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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Liberal" with various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the Liberal political party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĵĺ
    -0.77
    KT
    -0.72
    IDER
    -0.71
    oxide
    -0.69
     Ragnarok
    -0.68
    OHN
    -0.68
    ...]
    -0.66
    RIP
    -0.63
    OUT
    -0.63
    orks
    -0.63
    POSITIVE LOGITS
     Liberals
    1.04
     Liberal
    0.98
     councill
    0.82
    ité
    0.79
    naissance
    0.78
    tarian
    0.77
    Liberal
    0.77
    emouth
    0.76
     mascul
    0.75
     Conservatives
    0.74
    Act Density 0.007%

    No Known Activations