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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative health conditions, particularly focusing on physical and mental sickness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unlaw
    -0.75
     Unch
    -0.68
     principals
    -0.67
     Goodwin
    -0.67
    wcsstore
    -0.67
     sanctioned
    -0.66
     guid
    -0.64
     Noir
    -0.64
     Hier
    -0.62
     CLS
    -0.61
    POSITIVE LOGITS
    ening
    1.49
    ened
    1.34
    bay
    1.25
    nesses
    0.99
    ness
    0.93
    ly
    0.93
    er
    0.91
    estro
    0.90
    igue
    0.90
    ens
    0.89
    Act Density 0.054%

    No Known Activations