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

    Neuronpedia

    INDEX
    Explanations

    indicators of suspicion and advisory roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isko
    -0.17
    errick
    -0.16
    isky
    -0.15
    ISK
    -0.14
    eware
    -0.14
    åĽ£
    -0.14
    IEWS
    -0.14
    IW
    -0.13
    eyh
    -0.13
    ertz
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥ«
    0.17
    olist
    0.16
    iert
    0.15
    azing
    0.15
    pricing
    0.15
    ABL
    0.14
    pliers
    0.14
    mán
    0.14
    swagen
    0.14
    걸
    0.14
    Act Density 0.593%

    No Known Activations