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

    Neuronpedia

    INDEX
    Explanations

    keywords related to political discussions and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    punctuations, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubi
    -0.79
    NK
    -0.75
     IPM
    -0.73
    heter
    -0.70
    erno
    -0.69
    hess
    -0.67
    enne
    -0.67
    nesty
    -0.67
    seed
    -0.66
    Clock
    -0.66
    POSITIVE LOGITS
    ?:
    0.76
    aido
    0.66
    andals
    0.66
     authored
    0.65
    ģĸ
    0.64
     mailed
    0.63
     aval
    0.61
     Helpful
    0.61
     Fenrir
    0.61
     Monsters
    0.61
    Act Density 0.000%

    No Known Activations