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

    Neuronpedia

    INDEX
    Explanations

    words related to organizations, titles, and political entities

    oai_token-act-pair · gpt-3.5-turbo

    words related to political systems and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lemon
    -0.62
    isks
    -0.61
    yright
    -0.58
     Jarrett
    -0.58
     nipples
    -0.58
     Farrell
    -0.57
     Monaco
    -0.57
     Rollins
    -0.56
    mind
    -0.55
     Yankee
    -0.54
    POSITIVE LOGITS
    et
    0.97
    entary
    0.91
    ocene
    0.76
    sembly
    0.75
    ittee
    0.74
    arthed
    0.72
    erver
    0.71
    ittees
    0.71
    emouth
    0.71
    ét
    0.69
    Act Density 0.076%

    No Known Activations