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

    Neuronpedia

    INDEX
    Explanations

    references to loyalty or love-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nicol
    -0.14
    PT
    -0.14
    adu
    -0.14
    lice
    -0.14
    844
    -0.14
    aná
    -0.14
    ëħIJ
    -0.13
     damer
    -0.13
    ubyte
    -0.13
    _stderr
    -0.13
    POSITIVE LOGITS
    seau
    0.18
    eliness
    0.18
    icrous
    0.18
    ely
    0.17
    alty
    0.17
    /lo
    0.17
    lei
    0.17
    ullo
    0.17
    elly
    0.17
    енз
    0.16
    Act Density 0.019%

    No Known Activations