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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotions or sensations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.84
    inka
    -0.77
    ourning
    -0.71
    ciating
    -0.70
     Shutterstock
    -0.70
    conservancy
    -0.69
    adish
    -0.68
    agh
    -0.67
     Mub
    -0.66
     Details
    -0.66
    POSITIVE LOGITS
     like
    1.00
     hollow
    1.00
     awfully
    0.93
     awkward
    0.93
     stale
    0.89
     oddly
    0.88
     strangely
    0.88
     comfortable
    0.87
     obligated
    0.86
     unnatural
    0.85
    Act Density 0.038%

    No Known Activations