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

    Neuronpedia

    INDEX
    Explanations

    political and policy-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to democratic rights and civic engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĢº
    -0.48
    pmwiki
    -0.44
    ãĥĦ
    -0.43
    PRE
    -0.43
    Copyright
    -0.43
    je
    -0.42
     Copyright
    -0.42
     constitu
    -0.42
    Gender
    -0.41
    ãĤ±
    -0.40
    POSITIVE LOGITS
     however
    0.62
     meanwhile
    0.59
     though
    0.57
     moreover
    0.45
    anwhile
    0.45
     phased
    0.43
    eering
    0.41
     --------------------
    0.40
     tho
    0.39
     therefore
    0.39
    Act Density 4.998%

    No Known Activations