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

    Neuronpedia

    INDEX
    Explanations

    entities compared as being similar or equivalent to one another

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.82
    ular
    -0.64
     Pastebin
    -0.63
    pat
    -0.63
    omatic
    -0.61
    elfth
    -0.61
    cel
    -0.60
    =-=-
    -0.60
     Ging
    -0.59
    NER
    -0.58
    POSITIVE LOGITS
     alike
    1.39
    soever
    0.86
    WHERE
    0.80
    lihood
    0.77
     rejoice
    0.77
     sexes
    0.75
     greets
    0.73
     strives
    0.71
     fascinated
    0.70
     perished
    0.69
    Act Density 0.025%

    No Known Activations