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

    Neuronpedia

    INDEX
    Explanations

    references to loyalty or loyal relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOC
    -0.15
    ei
    -0.15
    chin
    -0.15
    ogo
    -0.14
    oir
    -0.14
     Pest
    -0.14
    \Traits
    -0.13
    ÇIJ
    -0.13
     palette
    -0.13
    ENDED
    -0.13
    POSITIVE LOGITS
    ermen
    0.16
    656
    0.16
    inka
    0.15
     fishes
    0.15
    vinces
    0.15
    969
    0.15
    rypton
    0.15
    ForRow
    0.15
    amen
    0.14
    ajs
    0.14
    Act Density 0.001%

    No Known Activations