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

    Neuronpedia

    INDEX
    Explanations

    names of political figures and countries

    oai_token-act-pair · gpt-3.5-turbo

    instances of immediate actions or requests within political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omaly
    -0.70
     lineage
    -0.68
    Occ
    -0.64
    apter
    -0.63
     entropy
    -0.63
    Exper
    -0.62
     manuscript
    -0.62
    uyomi
    -0.59
     Wonderful
    -0.59
    TOR
    -0.58
    POSITIVE LOGITS
     applauded
    1.15
     congratulated
    1.14
     condemned
    1.07
     criticised
    1.05
     tweeted
    1.04
     condol
    1.03
     praised
    1.00
     denounced
    1.00
     reacted
    1.00
     urged
    1.00
    Act Density 0.652%

    No Known Activations