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

    Neuronpedia

    INDEX
    Explanations

    URLs and technical information like paper titles and author names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     withal
    -0.84
     blest
    -0.82
     unspeak
    -0.81
     tupperware
    -0.79
     indescri
    -0.77
     ecru
    -0.76
     gaily
    -0.75
     hoody
    -0.74
    mistak
    -0.73
     McLaugh
    -0.73
    POSITIVE LOGITS
     abbra
    0.69
     offerta
    0.67
     ‹
    0.66
     espressione
    0.65
     rossi
    0.62
     stili
    0.62
     espres
    0.61
     obblig
    0.61
     uniti
    0.60
     ristor
    0.60
    Act Density 0.198%

    No Known Activations