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

    Neuronpedia

    INDEX
    Explanations

    personal experiences and actions described with strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    themes related to mental health struggles and crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unison
    -0.74
     yourselves
    -0.68
     ourselves
    -0.64
     Engineers
    -0.64
     Coverage
    -0.56
     Efficiency
    -0.56
     guiName
    -0.56
     Their
    -0.55
     asses
    -0.55
     Sweep
    -0.55
    POSITIVE LOGITS
     remorse
    1.01
     himself
    0.79
     repent
    0.79
     voluntarily
    0.77
     impuls
    0.76
     medication
    0.76
     herself
    0.76
     quitting
    0.75
     confessed
    0.74
     regrets
    0.74
    Act Density 1.082%

    No Known Activations