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

    Neuronpedia

    INDEX
    Explanations

    terms of endearment or affectionate addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dear salutations and dearly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.61
     infil
    -0.60
     bandages
    -0.58
     hypno
    -0.57
     fusi
    -0.57
    athione
    -0.57
     foss
    -0.57
     NSS
    -0.56
     hydra
    -0.56
    orsing
    -0.56
    POSITIVE LOGITS
     dear
    1.91
    dear
    1.61
     Dear
    1.47
    Dear
    1.38
     DEAR
    1.37
     dearest
    1.17
    DEAR
    1.06
     queridos
    1.02
     dearly
    0.93
     querida
    0.84
    Act Density 0.002%

    No Known Activations