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

    Neuronpedia

    INDEX
    Explanations

    keywords related to rabbits

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    omething
    -0.88
    ician
    -0.84
    xit
    -0.83
    inen
    -0.80
    inia
    -0.68
    icians
    -0.68
    itutional
    -0.68
    cloth
    -0.67
    ructure
    -0.66
    igne
    -0.65
    POSITIVE LOGITS
    MQ
    0.95
     butter
    0.82
     ears
    0.81
     Butter
    0.79
     squirrel
    0.74
     republic
    0.71
     rabbit
    0.70
    bles
    0.70
    ble
    0.69
     hole
    0.69
    Act Density 0.071%

    No Known Activations