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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "loyal" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elope
    -0.15
    бав
    -0.15
    yb
    -0.14
    eko
    -0.14
    á»į
    -0.14
    orr
    -0.14
    -gap
    -0.14
     setError
    -0.14
    ropolis
    -0.14
    stage
    -0.13
    POSITIVE LOGITS
    alty
    0.23
     allegiance
    0.21
    loy
    0.20
    )prepare
    0.16
     loyalty
    0.15
    ists
    0.15
    ilty
    0.15
     Loy
    0.15
    ิà¸ļ
    0.15
    elps
    0.15
    Act Density 0.017%

    No Known Activations