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

    Neuronpedia

    INDEX
    Explanations

    repetitive use of the word "yet" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    connecting contrasting terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.51
     Jefus
    -0.47
     uſed
    -0.43
     poil
    -0.43
     bogotá
    -0.42
    MatInputModule
    -0.41
     fú
    -0.40
     Arabia
    -0.40
     anormal
    -0.39
    pitaux
    -0.39
    POSITIVE LOGITS
     yet
    1.37
    Yet
    1.23
     Yet
    1.23
    yet
    1.19
     YET
    0.98
     lecz
    0.88
     namun
    0.85
    Doch
    0.84
     Doch
    0.81
    ppure
    0.80
    Act Density 0.005%

    No Known Activations