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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles or authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mejía
    -0.99
     Monfieur
    -0.87
     itſelf
    -0.81
     myſelf
    -0.76
     Cárdenas
    -0.75
     ſon
    -0.74
     Guimarães
    -0.73
     fubject
    -0.72
     ſch
    -0.72
     ſta
    -0.71
    POSITIVE LOGITS
     JIM
    0.46
     del
    0.46
     Gea
    0.45
     Jof
    0.44
     River
    0.44
    fvar
    0.44
     Herr
    0.42
     jim
    0.42
    JIM
    0.41
     Mate
    0.40
    Act Density 0.290%

    No Known Activations