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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific type of structured arrangement or reference, particularly in the context of names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erse
    -0.15
    erk
    -0.15
    erver
    -0.14
    rab
    -0.14
    armac
    -0.14
    stru
    -0.14
     pads
    -0.14
    erton
    -0.14
    yg
    -0.14
    ern
    -0.14
    POSITIVE LOGITS
    ts
    0.26
    ting
    0.25
    tings
    0.24
    ters
    0.24
    ta
    0.23
    ted
    0.23
    table
    0.22
    tes
    0.20
    ty
    0.20
    tdown
    0.19
    Act Density 0.087%

    No Known Activations