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

    Neuronpedia

    INDEX
    Explanations

    terms related to political and health-related topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political issues and social justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nings
    -0.61
     Prison
    -0.58
    lich
    -0.58
    Rh
    -0.58
    catch
    -0.58
     Kore
    -0.56
     Huckabee
    -0.55
     Mobil
    -0.54
     Sandra
    -0.54
     Sailor
    -0.54
    POSITIVE LOGITS
    ngth
    0.87
    etheless
    0.82
    =""
    0.82
    ancial
    0.79
     alike
    0.79
     srf
    0.77
    bably
    0.74
    ogether
    0.73
     pairs
    0.71
    ï¸ı
    0.69
    Act Density 0.192%

    No Known Activations