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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words ending with 'd'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     susp
    -0.60
     Metatron
    -0.58
    ouf
    -0.58
     Fein
    -0.58
     juggling
    -0.57
     PID
    -0.56
     infertility
    -0.55
     DEF
    -0.55
    rawdownloadcloneembedreportprint
    -0.55
    UAL
    -0.54
    POSITIVE LOGITS
    generation
    1.01
    century
    0.95
    minute
    0.92
    chance
    0.86
    first
    0.79
    great
    0.77
    hop
    0.76
    mentioned
    0.75
    hitting
    0.74
    morning
    0.73
    Act Density 0.033%

    No Known Activations