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

    Neuronpedia

    INDEX
    Explanations

    references to a specific protein or molecule known as "Tre"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    wiſe
    -0.91
     MOP
    -0.86
    ArrowToggle
    -0.83
     ―――――
    -0.83
     CommandType
    -0.82
     houſe
    -0.82
    Czytaj
    -0.82
     uſe
    -0.81
    ñora
    -0.79
     uſed
    -0.79
    POSITIVE LOGITS
     Tre
    1.48
    Tre
    1.41
     TRE
    1.38
    TRE
    1.30
    tre
    1.27
     tre
    1.14
    Trev
    1.03
     Tremb
    0.96
     Trevor
    0.91
     Trello
    0.90
    Act Density 0.035%

    No Known Activations