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

    Neuronpedia

    INDEX
    Explanations

    expressions related to evaluation or concern

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pylab
    -0.76
     brooklyn
    -0.71
     ecru
    -0.69
     skimage
    -0.69
     psycopg
    -0.68
     Necess
    -0.68
     pymysql
    -0.67
     Mga
    -0.62
     heapq
    -0.61
     orlando
    -0.59
    POSITIVE LOGITS
     utop
    0.66
    AsUp
    0.61
     thuy
    0.60
     lapto
    0.59
    awtextra
    0.58
     tuong
    0.56
     vort
    0.54
     fars
    0.53
    Autoritní
    0.52
     bals
    0.52
    Act Density 0.063%

    No Known Activations