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

    Neuronpedia

    INDEX
    Explanations

    steps in a recipe or instruction format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.83
     Shakspeare
    -0.82
     DbSet
    -0.80
     métallique
    -0.80
     móvel
    -0.78
     myſelf
    -0.77
     itſelf
    -0.76
    Спољашње
    -0.76
     masculina
    -0.74
    Geplaatst
    -0.74
    POSITIVE LOGITS
     --
    0.56
    ge
    0.55
    ph
    0.55
     "
    0.54
    é
    0.52
     base
    0.52
    пи
    0.51
     et
    0.51
    RenderAtEndOf
    0.50
     quant
    0.49
    Act Density 0.021%

    No Known Activations