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

    Neuronpedia

    INDEX
    Explanations

    political figures with their party affiliations mentioned

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'R' in various contexts, particularly in reference to political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Buddha
    -0.63
     Mandela
    -0.63
     Howe
    -0.58
     glam
    -0.58
     Torah
    -0.56
     Veil
    -0.56
     Merkel
    -0.55
     Britann
    -0.55
     Schumer
    -0.54
     smugglers
    -0.54
    POSITIVE LOGITS
    .-
    0.96
    .,
    0.95
    -
    0.88
    -[
    0.87
    ivals
    0.82
    ector
    0.81
    INO
    0.78
    icky
    0.77
    -$
    0.77
    IA
    0.76
    Act Density 0.016%

    No Known Activations