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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to scientific processes and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     paper
    -0.53
     don
    -0.48
     Du
    -0.48
     Don
    -0.47
     Paper
    -0.46
     smart
    -0.46
     Kras
    -0.45
     Ari
    -0.45
     prud
    -0.45
    InputTagHelper
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.83
     Theſe
    0.81
     Roskov
    0.78
     Monfieur
    0.77
     myſelf
    0.77
    Попис
    0.77
     صوتيه
    0.76
     Majefty
    0.75
     themſelves
    0.72
     referenties
    0.72
    Act Density 0.696%

    No Known Activations