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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cherished or loved things or people

    oai_token-act-pair · gpt-3.5-turbo

    the word "beloved" and its variants, indicating a focus on endearment or affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DoS
    -0.72
    raviolet
    -0.72
    agnetic
    -0.70
    ramid
    -0.68
    enei
    -0.68
    clinical
    -0.67
    plan
    -0.67
    lining
    -0.67
    SPONSORED
    -0.66
    techn
    -0.65
    POSITIVE LOGITS
     beloved
    1.04
     dearly
    0.85
     cherished
    0.77
     darling
    0.75
     loved
    0.73
     venerable
    0.70
    reetings
    0.68
     Favorite
    0.68
     favourite
    0.67
    rily
    0.66
    Act Density 0.011%

    No Known Activations