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

    Neuronpedia

    INDEX
    Explanations

    the presence of the prefix "Tr" or variations of it in words

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ">//
    -0.90
     avoient
    -0.83
     Gregorian
    -0.82
    Jau
    -0.78
     fen
    -0.77
    fore
    -0.75
    Cow
    -0.75
    unknownFields
    -0.74
     }{\
    -0.74
    ########.
    -0.73
    POSITIVE LOGITS
     Tr
    1.16
    Tr
    0.94
     Trunk
    0.84
     tr
    0.81
     Truman
    0.81
     trunk
    0.79
     Trunks
    0.75
     Gabel
    0.75
     mellitus
    0.73
     trun
    0.71
    Act Density 0.013%

    No Known Activations