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

    Neuronpedia

    INDEX
    Explanations

    names and titles of political figures

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles of political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.69
    appropriate
    -0.69
    ickle
    -0.67
    igs
    -0.66
    fw
    -0.65
    yss
    -0.64
    spir
    -0.64
     applic
    -0.63
    ciation
    -0.61
    wise
    -0.61
    POSITIVE LOGITS
    ģĸ
    0.73
    bilt
    0.70
     Desmond
    0.66
    ãĤ¶
    0.66
     Olympia
    0.65
     Yugoslavia
    0.64
     convicted
    0.62
    turned
    0.62
     Judd
    0.62
     forgotten
    0.59
    Act Density 0.186%

    No Known Activations