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

    Neuronpedia

    INDEX
    Explanations

    patterns resembling ASCII art

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     comprim
    -0.55
     bezeichneter
    -0.54
    <bos>
    -0.54
     ladri
    -0.51
    khó
    -0.47
    تقاوى
    -0.47
     parten
    -0.46
     biling
    -0.46
    /*
    -0.45
     solidar
    -0.45
    POSITIVE LOGITS
     shewn
    0.59
     endeavouring
    0.57
    :,,
    0.57
     ftu
    0.56
     PLWABN
    0.56
     embodi
    0.55
     vns
    0.55
     apprehen
    0.54
     fign
    0.53
     poff
    0.53
    Act Density 1.331%

    No Known Activations