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

    Neuronpedia

    INDEX
    Explanations

    words related to obsession and fixation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     makro
    -0.52
     anonyme
    -0.50
     solidar
    -0.49
     boh
    -0.47
     geograf
    -0.47
     Völ
    -0.47
     Bakter
    -0.47
     dras
    -0.47
     alpina
    -0.47
     generali
    -0.47
    POSITIVE LOGITS
     obsession
    1.02
     obsessed
    0.95
     obses
    0.86
     obsessive
    0.80
    obses
    0.79
     dirait
    0.78
     Obs
    0.73
     fascination
    0.69
     preoccupation
    0.66
     pylab
    0.63
    Act Density 0.141%

    No Known Activations