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

    Neuronpedia

    INDEX
    Explanations

    references to specific genres or categorizations of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.84
     nakalista
    -0.83
     ſever
    -0.79
     ſtre
    -0.78
    ükemmel
    -0.78
     {:.
    -0.75
     Reſ
    -0.74
     houſe
    -0.74
     ſeveral
    -0.73
     deſt
    -0.72
    POSITIVE LOGITS
    ists
    0.73
     Estate
    0.66
    lists
    0.58
     affair
    0.58
    genre
    0.54
     InputDecoration
    0.54
     ESTATE
    0.51
     regain
    0.51
    Token
    0.50
    Estate
    0.50
    Act Density 0.088%

    No Known Activations