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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations or abbreviations associated with regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.42
    T
    -0.26
    TS
    -0.25
    n
    -0.24
    S
    -0.24
    SM
    -0.24
    sak
    -0.23
    TH
    -0.23
    TT
    -0.23
    TA
    -0.23
    POSITIVE LOGITS
    meric
    0.25
    utomation
    0.24
    uthor
    0.23
    merican
    0.23
    udio
    0.23
    zure
    0.22
    gain
    0.22
    O
    0.21
    utom
    0.21
    uto
    0.20
    Act Density 0.117%

    No Known Activations