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

    Neuronpedia

    INDEX
    Explanations

    mentions of or references to relatives

    oai_token-act-pair · gpt-3.5-turbo

    references to family or relatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oker
    -0.79
     Archdemon
    -0.78
    ococ
    -0.69
    forcing
    -0.68
    Cola
    -0.67
     Patton
    -0.66
    oted
    -0.65
    awar
    -0.64
    yx
    -0.64
     Dome
    -0.63
    POSITIVE LOGITS
     relatives
    1.03
    hips
    0.96
    hesis
    0.93
    hetical
    0.91
    heses
    0.86
    hetically
    0.81
     ancest
    0.80
    hes
    0.78
    hood
    0.77
    ilial
    0.77
    Act Density 0.016%

    No Known Activations