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

    Neuronpedia

    INDEX
    Explanations

    the word "thus" and its variations, indicating conclusions or transitions in reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pring
    -0.79
     Frankie
    -0.71
     PVP
    -0.71
    lipop
    -0.71
    Okey
    -0.71
     Alton
    -0.70
     Remo
    -0.69
     Apre
    -0.68
    pee
    -0.67
     PFA
    -0.65
    POSITIVE LOGITS
     propOrder
    1.06
    ly
    1.00
     thus
    0.87
    Lähteet
    0.80
    ابراین
    0.76
    thus
    0.76
    TintMode
    0.75
     Thus
    0.75
    VIAF
    0.74
    InputTagHelper
    0.74
    Act Density 0.100%

    No Known Activations