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

    Neuronpedia

    INDEX
    Explanations

    social controversies and conflicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     increa
    -0.85
     michelin
    -0.85
     fortn
    -0.83
     reluct
    -0.83
     désol
    -0.82
     encomp
    -0.82
     shenan
    -0.81
     nephe
    -0.79
     Manufact
    -0.77
     secon
    -0.77
    POSITIVE LOGITS
     dared
    0.57
    <?
    0.57
     slightest
    0.56
     кӀ
    0.54
    hatenablog
    0.51
    toPromise
    0.50
     =>'
    0.48
    oara
    0.48
    liothèque
    0.48
    álbum
    0.47
    Act Density 0.516%

    No Known Activations