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

    Neuronpedia

    INDEX
    Explanations

    contractions of 'is'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    wright
    -0.97
    este
    -0.85
    VO
    -0.74
    bear
    -0.73
    then
    -0.73
    ships
    -0.71
    fo
    -0.71
    ova
    -0.71
    robe
    -0.70
    yrights
    -0.69
    POSITIVE LOGITS
     edition
    1.14
     episode
    0.98
     installment
    0.95
     announcement
    0.94
     iteration
    0.92
     editions
    0.89
     arrival
    0.88
     deadline
    0.87
     festivities
    0.86
     inaugural
    0.81
    Act Density 0.098%

    No Known Activations