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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to negative emotions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    JoinTable
    -0.60
     ElementRef
    -0.58
    تقاوى
    -0.57
    meyi
    -0.57
     rendono
    -0.56
    çalves
    -0.55
     OnDestroy
    -0.54
    tréal
    -0.54
    éndez
    -0.54
    mesini
    -0.53
    POSITIVE LOGITS
     mef
    0.92
     intersper
    0.91
     fta
    0.88
     fuj
    0.86
     nmax
    0.84
     levis
    0.82
     yves
    0.81
     triton
    0.81
     alberto
    0.79
     lts
    0.79
    Act Density 0.521%

    No Known Activations