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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of 'July' followed by a numerical day

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    corn
    -0.70
    ifles
    -0.63
     reluct
    -0.61
    strate
    -0.60
    Interstitial
    -0.59
     calibr
    -0.59
    hyde
    -0.59
     hob
    -0.58
     exha
    -0.57
    fect
    -0.57
    POSITIVE LOGITS
     31
    1.00
    hew
    0.97
     29
    0.91
     Fourth
    0.90
    esville
    0.89
     28
    0.85
     26
    0.84
     27
    0.84
    bourne
    0.84
     23
    0.83
    Act Density 0.025%

    No Known Activations