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

    Neuronpedia

    INDEX
    Explanations

    countries, cities, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    the end-of-text token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilar
    -0.61
    ãĤ¦ãĤ¹
    -0.61
    atever
    -0.60
    bler
    -0.59
    ueless
    -0.58
    akespe
    -0.56
    herer
    -0.55
    farious
    -0.55
    ilaterally
    -0.55
    ttes
    -0.54
    POSITIVE LOGITS
     analyst
    0.61
     officials
    0.61
     reacts
    0.58
     archaeologists
    0.56
     awoke
    0.55
     mourn
    0.55
     spokesman
    0.55
     intends
    0.54
    zbollah
    0.53
     Oversight
    0.53
    Act Density 0.372%

    No Known Activations