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

    Neuronpedia

    INDEX
    Explanations

    specific patterns and endings in words related to topics of finance or transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.20
    halt
    -0.18
    er
    -0.18
    eri
    -0.18
    hur
    -0.18
    erse
    -0.18
    erd
    -0.17
    erb
    -0.17
    erland
    -0.17
    hoo
    -0.17
    POSITIVE LOGITS
    ted
    0.41
    ters
    0.39
    ting
    0.34
    tings
    0.33
    tes
    0.31
    ts
    0.28
    ta
    0.27
    ti
    0.25
    ropolis
    0.24
    ty
    0.24
    Act Density 0.125%

    No Known Activations