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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and emotions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.87
    ifully
    -0.73
    moil
    -0.72
    voy
    -0.71
    iful
    -0.66
    vic
    -0.66
    raltar
    -0.64
    tex
    -0.64
    ERY
    -0.63
    çļ
    -0.62
    POSITIVE LOGITS
     bothered
    1.00
     bother
    0.95
     anymore
    0.93
     bothering
    0.89
     cared
    0.84
    hin
    0.80
     mattered
    0.79
     fit
    0.79
     appreciated
    0.76
     anywhere
    0.74
    Act Density 0.032%

    No Known Activations