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

    Neuronpedia

    INDEX
    Explanations

    identifiers or relationships between individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    inen
    -0.75
    Cola
    -0.69
    erd
    -0.68
    inem
    -0.67
    inth
    -0.67
    isconsin
    -0.66
    urrent
    -0.65
    ERG
    -0.65
    iman
    -0.65
    ococ
    -0.64
    POSITIVE LOGITS
     relatives
    0.97
    hips
    0.85
    ilial
    0.81
    hood
    0.80
     cousins
    0.79
     ancestors
    0.78
     surn
    0.77
     dolls
    0.75
    rieved
    0.74
     nephew
    0.72
    Act Density 0.044%

    No Known Activations