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

    Neuronpedia

    INDEX
    Explanations

    phrases related to computer programming languages and technologies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     accordingly
    -0.65
    herer
    -0.64
     beforehand
    -0.61
     afterwards
    -0.59
    *.
    -0.58
    ÃĥÃĤ
    -0.57
    entimes
    -0.57
    ornings
    -0.57
     theirs
    -0.56
    /"
    -0.55
    POSITIVE LOGITS
     simplest
    0.74
    ses
    0.73
     same
    0.73
    resa
    0.72
     smallest
    0.72
     foregoing
    0.72
    oret
    0.72
     hottest
    0.72
     Clintons
    0.71
     largest
    0.69
    Act Density 0.737%

    No Known Activations